feat(equinor): tailored AI Architect resume + cover letter package
Pass 2 critique 80.0/100 (honest-stretch reach app, converged near ceiling). Includes accuracy fix: Swisscom Data Mesh reframed from sole-build to company-wide migration contributed to (hedged verbs); orchestration + reference-architecture surfaced; removed -ing bullet trailers; CL trimmed to 300 words with matching ownership hedge. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
@@ -137,6 +137,7 @@ _Update this section when starting/finishing a JD._
|
||||
| Apple Data Engineer (ISE, Zurich) | Critique DONE Pass 1 (78.5/100) | /edit-resume for Tier 1 fixes or submit |
|
||||
| Kraken AI Infrastructure | Critique DONE Pass 2 (84.5/100) — converged near max | Submit, or apply Tier 2 polish (agent orchestration / guardrails in skills) |
|
||||
| Google FDE GenAI (Zurich) | PAUSED — GenAI evidence gap too large; redirecting to data-eng/MLOps roles | Likely abandon |
|
||||
| Equinor AI Architect (Norway) | Critique DONE Pass 2 (80.0/100) — converged near ceiling ~81; Data Mesh overclaim fixed | Submit / finalize PDFs |
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -0,0 +1,110 @@
|
||||
Manager / AI Architect – Agentic systems
|
||||
Apply
|
||||
|
||||
locations
|
||||
Stavanger, Norway
|
||||
Oslo, Norway
|
||||
Rotvoll, Norway
|
||||
Sandsli, Norway
|
||||
|
||||
posted on
|
||||
Posted 5 Days Ago
|
||||
|
||||
job requisition id
|
||||
JR106747
|
||||
|
||||
Important! To make sure your application is considered, please submit it before the end of the day on (dd.mm.yyyy):
|
||||
05.06.2026
|
||||
|
||||
We encourage candidates to apply as soon as possible.
|
||||
|
||||
What does the job involve?
|
||||
Shape how Equinor designs and scales agentic AI solutions—working at the intersection of architecture, engineering, and responsible AI.
|
||||
|
||||
Equinor is building the foundation for enterprise-scale agentic AI, and this role offers a rare opportunity to play a key role in that journey. You will architect solutions, make key design decisions, guide delivery with AI and ML engineering teams, and ship production systems that automate workflows and sharpen decisions across multiple business areas.
|
||||
|
||||
What will my tasks be?
|
||||
|
||||
Within this position, your key tasks will be to:
|
||||
|
||||
Shape and apply reference architecture for agentic systems, translating standards, design principles, and guardrails into practical solution patterns across Equinor.
|
||||
|
||||
Architect and deliver production agents: orchestration, grounded retrieval, structured LLM integrations with enterprise APIs, MCP-based tool/data access, and multimodal document understanding.
|
||||
|
||||
Drive solution strategy, technology choices, and architectural blueprints for key use cases; align stakeholders, engineering teams, and partners; and provide technical leadership from concept through scaled deployment.
|
||||
|
||||
Embed safety, compliance, and privacy by design; align with GDPR and the EU AI Act; enforce policy as code and safe tool execution; and manage uncertainty in non-deterministic systems by surfacing confidence, bounding autonomy, routing to human oversight, and providing safe fallback and rollback paths.
|
||||
|
||||
Raise the bar on engineering quality and long-term capability by improving performance, reliability, and cost efficiency, while mentoring peers and building reusable foundations for future AI solutions.
|
||||
|
||||
Here's what we expect from you:
|
||||
|
||||
At Equinor, there are some overall qualities we regard as essential. We want you to identify with the values that guide our decisions and help us succeed and grow: open, collaborative, courageous and caring. We expect you to make safety your priority and to contribute to our zero-harm culture. And for this specific position, we are also looking for:
|
||||
|
||||
Required qualifications
|
||||
|
||||
Master’s or PhD in Computer Science, Data Science, Machine Learning, Linguistics, or related field.
|
||||
|
||||
Strong architectural experience across data, model, and application layers, with sound judgment on trade-offs, scalability, risk, and compliance in enterprise AI systems.
|
||||
|
||||
Proven ability to navigate ambiguity, set technical direction within a broader architecture, align stakeholders, and convert strategy into delivery.
|
||||
|
||||
Hands-on with modern LLMs and agent frameworks (e.g., LangGraph, AutoGen, LangChain/LlamaIndex, Semantic Kernel).
|
||||
|
||||
NLP and generative AI expertise, including prompt design, RAG architectures, model evaluation, and practical experience with major LLM providers and open-source models.
|
||||
|
||||
Solid Python and software engineering fundamentals (testing, CI/CD, version control).
|
||||
|
||||
Track record of delivering AI solutions from concept to production, with measurable business impact.
|
||||
|
||||
Preferred qualifications
|
||||
|
||||
Technical leadership: mentoring, communities, publishing, speaking, or open-source contributions.
|
||||
|
||||
Multimodal AI: document and image understanding, diagram Q&A, speech-to-text.
|
||||
|
||||
Responsible AI: PII handling, red-teaming, content moderation, risk assessment, regulatory compliance.
|
||||
|
||||
Containers and cloud: Docker, Kubernetes; Azure (Azure ML, AKS, Azure OpenAI, storage, networking).
|
||||
|
||||
Integration: APIs, events/messaging, standardised data and tool access via MCP.
|
||||
|
||||
Why join us?
|
||||
|
||||
If you are motivated by architecting practical AI solutions, working on technically demanding challenges, and helping scale responsible agentic AI in a major energy company, we would love to hear from you.
|
||||
|
||||
What can we offer you?
|
||||
|
||||
We want you to have a rewarding and fulfilling work life. That’s why we offer:
|
||||
|
||||
Not just a job - a career
|
||||
|
||||
In Equinor, your development begins on day one. You will build your competence through a wide range of learning activities while being empowered to build your career across multiple disciplines and geographies. Our internal job market allows a wide range of opportunities for development and growth within your own field, or even in other areas you find interesting and relevant.
|
||||
|
||||
Attractive rewards
|
||||
|
||||
We give you a comprehensive benefits package with a competitive salary, global parental leave, bonus scheme and pension plan.
|
||||
|
||||
Wellness and work-life balance
|
||||
|
||||
We care about and prioritise our employees’ well-being. We know that for you to be the best version of yourself in the workplace, being able to collect your children, attend a class or simply enjoy social time can be invaluable. That’s why we encourage you to make use of our flexible work arrangements wherever possible.
|
||||
|
||||
An inclusive culture
|
||||
|
||||
We believe embracing our differences makes us stronger. For us, true inclusion means being able to bring your whole self to work, and for you and everyone else to feel accepted and valued.
|
||||
|
||||
Equal opportunities for everyone
|
||||
|
||||
Equinor is an equal-opportunity employer. We make all employment decisions, which include hiring, promotion, transfer, demotion, termination, and training, without regard to race, colour, religion, sex, sexual orientation, gender identity, national origin, age, disability, marital status, parental status, veteran status, or any other protected status.
|
||||
|
||||
As part of this commitment, reasonable adjustments will be made during the recruitment process for candidates with disabilities or long-term health conditions. If you have any specific requirements, please clarify this in your application and our team will be in contact to see how we can support your needs.
|
||||
|
||||
We also believe everyone should be paid fairly and consistently for their contribution to our collective success. To ensure fairness and transparency, positions at Equinor are evaluated using our global job architecture based on the position’s responsibilities, complexity, and impact, and regularly reviewed to ensure consistency and alignment across the organisation.
|
||||
|
||||
Important notes about the application process
|
||||
|
||||
We expect you to openly offer all relevant information about yourself during the recruitment process. Background checks are performed on all final candidates, and all permanent and temporary hires will be screened using relevant sanctions lists to ensure compliance with sanctions laws. When applying for a job in Norway you will be asked for information on affiliation to high-risk countries for a security assessment.
|
||||
|
||||
About Equinor
|
||||
|
||||
Equinor is an international energy company headquartered in Norway, energising the lives of 170 million people worldwide. Our ambition is to be a leading company in the energy transition and achieve net zero by 2050. Our task is enormous: supplying the world with the energy it needs, while lowering emissions to the atmosphere. To achieve it, we are looking for like-minded people to join our team of 25,000 colleagues working in more than 20 countries. We’re up for the challenge. Are you?
|
||||
@@ -0,0 +1,257 @@
|
||||
# Critique: Equinor — Manager / AI Architect, Agentic Systems (JR106747)
|
||||
|
||||
**Resume File:** `output/Equinor_AI_Manager/e2e_equinor_ai_manager_resume.tex`
|
||||
**Cover Letter:** `output/Equinor_AI_Manager/e2e_equinor_ai_manager_cover_letter.tex`
|
||||
**Date:** 2026-05-27
|
||||
**Pass:** 2 (re-score after Edit 1; lens reused from Pass 1, not re-researched)
|
||||
|
||||
---
|
||||
|
||||
## Changes Since Pass 1 (Edit 1, 2026-05-27)
|
||||
|
||||
Trajectory: **Pass 1 = 77.5 → Pass 2 = 80.0** (+2.5).
|
||||
|
||||
| Edit | Effect |
|
||||
|---|---|
|
||||
| SW-7 verb fix ("Built a Data Mesh" → "Helped move Swisscom off legacy Teradata… modelled and built governed data products and onboarded source systems…") | Removed the sole-ownership **overclaim**; surfaced **data-layer architecture** (modelling/design) honestly; bold trimmed so it holds 2 lines (193 chars) |
|
||||
| Summary hedge ("Software and AI engineer"; "design and build governed data products on the company's AWS Data Mesh") | Accuracy + slightly stronger identity; no "Solution Architect" self-title (correct) |
|
||||
| Skills: +`orchestration`, +`reference architecture` (dropped redundant "model deployment" / "data catalog") | Two JD terms now verbatim → ATS up |
|
||||
| Tier 2: removed 3 `-ing` participial trailers (B4/B8/B10) | AI-fingerprint clean; bullets end on concrete objects |
|
||||
| CL: 313→300 words + same ownership hedge in P2 | Within industry word target; package cohesion preserved (no contradiction with revised resume) |
|
||||
|
||||
**Re-scored dimensions only** (others unchanged from Pass 1):
|
||||
- **ATS 8.0 → 8.5** — orchestration + reference architecture now present; ~18/20.
|
||||
- **Summary 7.5 → 8.0** — hedged, honest, data-product-design identity.
|
||||
- **Bullets 7.5 → 8.0** — overclaim fixed, `-ing` trailers gone, data-layer architecture surfaced (still no metrics — accepted per user).
|
||||
- **Narrative 8.0** (unchanged), **Skills 8.5** (unchanged), **Credibility 7.5** (unchanged — honesty fix is a wash with the still-absent metrics/management), **Visual 7.5** (unchanged), **Credentials 7.5** (unchanged).
|
||||
|
||||
**Verdict:** Converged near the achievable ceiling (~81 with metrics excluded per user; hard ceiling ~83 on structural gaps). No remaining Tier 1 fixes. **Submit.**
|
||||
|
||||
---
|
||||
|
||||
> **Strategic frame (from session file):** HONEST STRETCH / reach application. Required agent-framework + GenAI-architecture + formal-management evidence is thin. Positioned as senior production-AI/MLOps engineer with architecture breadth reaching toward agentic architect — not a checkbox match. Critique scores against that reality, not against an imaginary perfect-fit candidate.
|
||||
|
||||
---
|
||||
|
||||
## Domain-Specialist Lens (researched for this JD)
|
||||
|
||||
### Reviewer Persona
|
||||
Equinor AI/ML architecture lead or principal engineer in the AI & ML Engineering org (Stavanger/Oslo). Runs industrial ML at scale already — Omnia data platform on Azure, EurekaML, Prevent (520+ production models on rotating equipment). Pragmatic about the demo-to-production gap; has watched the 2025/26 agentic hype cycle and knows ~11% of enterprises actually run agents in production. **Impressed by:** real production ML under operational constraints, reliability/safety rigor, honest responsible-AI substance, architecture judgment across layers. **Bored/alarmed by:** agent-framework name-dropping with no depth, inflated GenAI claims, "I built an agent in a notebook" framed as production. Has likely seen 80–150 applications for a role this senior and visible.
|
||||
|
||||
### Company Context
|
||||
International energy company, HQ Norway, net-zero-by-2050, ~25k staff, energising 170M people. This role builds the *foundation* for enterprise-scale agentic AI: reference architecture, production agents (orchestration, grounded retrieval, MCP tool access, multimodal doc understanding), responsible AI (GDPR/EU AI Act, policy-as-code, bounded autonomy, human oversight, safe fallback/rollback), engineering-quality uplift, mentoring. Tech reality: Azure-native (Omnia, EurekaML on Azure ML/Synapse/Cosmos), Prevent saved ~$130M in 2025 via predictive maintenance. Culture: open/collaborative/courageous/caring, safety-first / zero-harm.
|
||||
|
||||
### JD Vocabulary Extraction (top terms, ranked)
|
||||
| # | JD Term | Freq / Placement | Meaning at Equinor | Resume Match? |
|
||||
|---|---------|------------------|--------------------|---------------|
|
||||
| 1 | **architecture / AI Architect** | Title + repeated (reference architecture, blueprints, architect solutions, across data/model/app layers) | Set technical direction & solution patterns across the org | **PARTIAL — under-foregrounded** |
|
||||
| 2 | agentic AI / agents | Title + body, ~5x | Production agents that automate workflows & sharpen decisions | YES (agentic workflows) |
|
||||
| 3 | agent frameworks (LangGraph/AutoGen/LangChain/LlamaIndex/Semantic Kernel) | Required qual, named | Hands-on framework depth | **NO — intentional honest gap** |
|
||||
| 4 | grounded retrieval / RAG | Body | Agents query governed data | YES |
|
||||
| 5 | MCP-based tool/data access | Body + preferred | Standardised tool access | YES (MCP tooling / MCP-based) |
|
||||
| 6 | structured LLM integration w/ enterprise APIs | Body | LLM-to-system wiring | YES (LiteLLM gateway) |
|
||||
| 7 | orchestration | Body | Multi-step agent control | **NO — not verbatim** |
|
||||
| 8 | multimodal document/image understanding, diagram Q&A, speech-to-text | Preferred | Doc understanding for agents | PARTIAL (image + speech YES; "document understanding" NO) |
|
||||
| 9 | responsible AI / GDPR / EU AI Act / policy-as-code / bounded autonomy / human oversight / safe fallback+rollback | Body, heavy | Safe non-deterministic systems | YES (strong) |
|
||||
| 10 | concept → production, measurable business impact | Required | Ship, don't prototype | YES on concept→prod; **WEAK on measurable impact (no metrics)** |
|
||||
| 11 | Python + SWE fundamentals (testing, CI/CD, version control) | Required | Engineering rigor | YES |
|
||||
| 12 | Azure (Azure ML, AKS, Azure OpenAI) | Preferred | Their actual cloud | **NO — intentional honest gap (AWS instead)** |
|
||||
| 13 | technical leadership / mentoring / publishing / speaking / OSS | Preferred | Influence beyond self | PARTIAL (mentoring/leadership YES; publishing/OSS/speaking NO) |
|
||||
| 14 | Manager / people leadership | Title | Lead engineering teams | **NO — intentional honest gap** |
|
||||
|
||||
### Domain Vocabulary Map
|
||||
| Resume Currently Says | Should Say for THIS JD | Why |
|
||||
|---|---|---|
|
||||
| Tagline: "AI/ML Engineer \| Agentic Data Foundations..." | Surface **"Solution Architecture"** in tagline | Role title is *AI Architect*; candidate holds AWS SAA + iSAQB CPSA — architecture is an honest, on-title signal currently hidden |
|
||||
| Summary: "Software engineer with 11+ years..." | "Software/AI engineer and **solution architect**..." | Reviewer scans for architecture in first 2 lines; "software engineer" reads junior-er than the role |
|
||||
| "agentic workflows query for grounded retrieval" | add **orchestration** where truthful (K8s/pipeline orchestration, agent workflow orchestration) | JD names orchestration as a core agent task; currently absent verbatim |
|
||||
| "image classification, speech recognition, multimodal" | add **document understanding** if truthful | Preferred qual phrase; image+speech present but not "document" |
|
||||
| iSAQB CPSA buried at cert #4 | promote architecture cert visibility | Direct "Software Architecture" credential for an Architect role |
|
||||
|
||||
### Gap Ranking
|
||||
- **Fatal (cause rejection at a strict screen):** Named agent frameworks (LangGraph/AutoGen/Semantic Kernel) — required qual, named, zero match. This is the structural ceiling and is *intentionally* not bridged (anti-fabrication). No mitigation possible without real experience.
|
||||
- **Serious (competitive candidates will have):** Azure depth (their cloud); measurable business-impact metrics; formal people-management (role says "Manager"); production RAG + formal model evaluation.
|
||||
- **Cosmetic (most candidates also miss):** publishing/speaking/OSS; red-teaming/content moderation; diagram Q&A.
|
||||
|
||||
### Methodology Transfer Test
|
||||
| Achievement | How Equinor's expert sees it |
|
||||
|---|---|
|
||||
| Bosch ML inference in 24/7 fab (BS-1) | "Direct analogue to Prevent — always-on industrial ML on safety-critical assets, no maintenance window. This is exactly our operating regime." **Transfers cleanly.** |
|
||||
| AWS Data Mesh / governed data products (SW-7) | "This is our Omnia, on the other cloud — governed data layer agents ground against. Architecture-relevant." **Transfers, but on AWS not Azure.** |
|
||||
| LiteLLM gateway + custom GPTs (SW-GenAI) | "Real LLM integration plumbing, multi-provider. Not agent-framework orchestration, but honest adjacent." **Partial transfer.** |
|
||||
| Security Champion + GDPR/governance (SW-5) | "Responsible-AI substance, not buzzwords — maps to our EU AI Act / policy-as-code mandate." **Transfers.** |
|
||||
| K8s + CI/CD + rollback (SW-3) | "Engineering-quality and safe-rollout discipline we want." **Transfers.** |
|
||||
|
||||
Four of five transfer cleanly or partially — the reframing largely worked. The one that *can't* be written honestly is "hands-on with LangGraph/Semantic Kernel," and the resume correctly does not pretend otherwise.
|
||||
|
||||
### Competitive Landscape
|
||||
- **Obvious-fit candidate:** Has shipped LLM agents with LangGraph/Semantic Kernel on **Azure OpenAI** + production RAG, ideally with an architecture title and some team leadership. Probably has a conference talk or OSS repo.
|
||||
- **Our advantage:** Rarer industrial **zero-downtime production-ML** credibility (Bosch fab ↔ Prevent), genuine security/governance/responsible-AI discipline, and authentic **Norway fit** (year in Bergen, basic Norwegian, ready to relocate). We win on reliability + responsibility + culture/relocation, not on agentic-framework hours.
|
||||
- **Their advantage:** Named-framework hands-on, Azure, formal management, possibly publishing. Several of these are structural and uncloseable truthfully right now.
|
||||
|
||||
---
|
||||
|
||||
## Five-Perspective Read-Through
|
||||
|
||||
### ATS Robot (keyword scan)
|
||||
| JD Keyword | Match |
|
||||
|---|---|
|
||||
| agentic AI / agents | YES |
|
||||
| architecture / reference architecture | PARTIAL (no "reference architecture"; "architecture" weak) |
|
||||
| orchestration | NO |
|
||||
| grounded retrieval | YES |
|
||||
| RAG | YES |
|
||||
| LLM integration / LLM providers | YES (multi-provider via LiteLLM) |
|
||||
| MCP | YES |
|
||||
| multimodal / image / speech-to-text | YES |
|
||||
| document understanding | NO |
|
||||
| prompt design | YES |
|
||||
| model evaluation | YES |
|
||||
| responsible AI / GDPR / EU AI Act | YES |
|
||||
| policy-as-code / human-in-the-loop / fallback+rollback | YES |
|
||||
| Python / CI/CD / version control | YES |
|
||||
| Docker / Kubernetes | YES |
|
||||
| concept-to-production | YES |
|
||||
| measurable business impact | WEAK (no metric) |
|
||||
| mentoring / technical leadership | YES |
|
||||
| agent frameworks (named) | NO (intentional) |
|
||||
| Azure | NO (intentional) |
|
||||
|
||||
**Match rate:** ~16/20 ≈ 80% → **PASS.** Misses split into *fixable* (orchestration, reference architecture, document understanding) and *intentional honest gaps* (named frameworks, Azure).
|
||||
|
||||
### Recruiter Glance (10 seconds)
|
||||
**Verdict: Maybe → Forward (≈55%).** Strong current title (Staff … AI Engineer at Swisscom), Bern→Norway relocation stated up front, AWS SAA visible. Friction: tagline and summary self-label "AI/ML Engineer / Software engineer" rather than the *Architect* the req is titled for — a recruiter pattern-matching the title may hesitate.
|
||||
|
||||
### HR Screen (30 seconds)
|
||||
**Verdict: Borderline → Phone screen (≈50%).** Master's ✓, Python ✓, production AI ✓, GDPR ✓. The named-agent-framework required qual is unmet and an HR checklist screen may catch it. Summary bridge is good but doesn't say "architecture."
|
||||
|
||||
### Hiring Manager (2 minutes)
|
||||
**Verdict: Maybe (≈30–40%).** This is the decisive reader and the honest crux.
|
||||
**Top 3 observations:**
|
||||
1. "Bosch 24/7 fab ML = our Prevent regime. Rare and real — this person has actually operated always-on industrial ML." (Strong positive.)
|
||||
2. "Genuine responsible-AI/governance substance, not buzzwords. Good for our EU AI Act mandate."
|
||||
3. "But no named agent-framework hands-on, no Azure, no quantified impact, and it's a *Manager* role with no people-management shown." (The cap.)
|
||||
**Predicted first interview question:** *"Walk me through the most complex LLM/agent integration you've built end-to-end — what orchestration and tool-access patterns did you use, and where did it run in production?"* (This probes exactly the soft spot; bridge points below prepare for it.)
|
||||
|
||||
### Technical Reviewer (10 minutes)
|
||||
**Truthfulness: one overclaim caught (now corrected in Tier 1).** The SW-7 bullet "Built a Data Mesh…" implied sole ownership of a *company-wide* platform migration — user confirmed he contributed to it, not solo-built it. Hedged rewrite in Tier 1. Other spot checks clean:
|
||||
- Security Champion "(2025/26)" — matches correction log (not 3 years, not an award). ✓
|
||||
- No LangChain/LangGraph/LlamaIndex/Semantic Kernel/AutoGen anywhere. ✓
|
||||
- No Azure claim. ✓
|
||||
- Languages: German/English/Norwegian only (no French/Italian boilerplate). ✓
|
||||
- Generali = Hamburg. ✓ Bosch = Dresden. ✓ Vizrt = Bergen (reinforces Norway thread). ✓
|
||||
- "11+ years" (2015→2026). ✓
|
||||
- CL hooks (Prevent 520+ models, ~$130M) — verified in session. ✓
|
||||
- "AWS Solutions Architect" in summary = held cert, accurate framing.
|
||||
**Consistency: clean** — CL claims all trace to resume bullets; no new unsupported achievements. **One AI-fingerprint flag** (below): three bullets end on participial trailers ("enabling…", "providing…", "supplying…").
|
||||
|
||||
---
|
||||
|
||||
## Eight-Dimension Scoring
|
||||
|
||||
| Dimension | Score | Weight | Weighted | Notes |
|
||||
|---|---|---|---|---|
|
||||
| ATS Keywords | 8.5/10 | 15% | 1.275 | ↑ orchestration + reference architecture now verbatim (~18/20) |
|
||||
| Summary | 8.0/10 | 10% | 0.80 | ↑ hedged + honest "Software and AI engineer"; data-product-design identity |
|
||||
| Skills Section | 8.5/10 | 10% | 0.85 | Excellent group names, honest, strong domain signal; add orchestration/reference-architecture |
|
||||
| Bullet Quality | 8.0/10 | 25% | 2.00 | ↑ overclaim fixed, `-ing` trailers gone, data-layer architecture surfaced; no metrics (accepted per user) |
|
||||
| Publications/Credentials | 7.5/10 | 10% | 0.75 | No pubs (honest gap vs obvious fit); certs strong (AWS SAA, iSAQB CPSA, IBM AI Eng) but CPSA buried |
|
||||
| Narrative Coherence | 8.0/10 | 15% | 1.20 | Clean arc; Bergen→Norway thread reinforces relocation; architecture under-threaded vs title |
|
||||
| Page Fill & Visual | 7.5/10 | 5% | 0.375 | Compiles clean, 2pp, 0 em-dashes; page 2 ~30% empty (underfill) |
|
||||
| Credibility Signals | 7.5/10 | 10% | 0.75 | Bosch 24/7 fab rare+credible; lacks quantified impact and any management evidence for a "Manager" role |
|
||||
| **Total** | | **100%** | **80.0** | Pass 1 77.5 → **Pass 2 80.0** (+2.5) |
|
||||
|
||||
**Score: 80.0/100 (Pass 2)** — converged near the achievable ceiling (~81 with metrics excluded per user; hard ceiling ~83 on structural gaps: named frameworks / Azure / people-management). No remaining Tier 1 fixes. **Submit.**
|
||||
|
||||
---
|
||||
|
||||
## Interview Likelihood
|
||||
|
||||
| Reader | Probability | Key Factor |
|
||||
|--------|------------|------------|
|
||||
| ATS | ~80% | Keyword coverage strong; risk only if filter hard-requires a named framework |
|
||||
| Recruiter (10s) | ~55% | Title-vs-tagline mismatch (Engineer vs Architect) |
|
||||
| HR (30s) | ~50% | Named-framework required qual unmet |
|
||||
| Hiring Manager (2m) | ~30–40% | Bosch/Prevent analogue + responsible-AI substance vs framework/Azure/management gap |
|
||||
| Technical Panel (10m) | CONCERNS (credible) | Real MLOps/infra depth; thin on agentic-framework orchestration |
|
||||
|
||||
### Ceiling Analysis
|
||||
| Scenario | Est. Score |
|
||||
|---|---|
|
||||
| Current | 77.5 |
|
||||
| + Tier 1 (architecture foreground + orchestration + CPSA surface + 1 real metric) | ~80.5 |
|
||||
| Theoretical max (this candidate + this JD) | ~82 |
|
||||
| Hard ceiling (structural: no named frameworks / Azure / people-mgmt) | ~83 |
|
||||
| What would close the gap | One real hands-on project with a named agent framework (LangGraph/Semantic Kernel) **+** one quantified production-impact metric → +3–4 pts and changes the HM verdict |
|
||||
|
||||
---
|
||||
|
||||
## Actionable Improvements
|
||||
|
||||
### Tier 1 (HIGH — do these; ~+2 pts total)
|
||||
|
||||
> **Verb-discipline correction (user-confirmed 2026-05-27):** The Swisscom Data Mesh / One Data Platform (ODP) is a *company-wide* migration off legacy Teradata DWH that Dennis **contributed to from the start** — he was NOT the sole driver. His genuine ownership: logical/physical **data modelling** and design of new data products, the implementation, **onboarding source systems** onto the ODP, and as Staff engineer **guiding/mentoring colleagues** on what & how to build (plus helping stand up the new platform's dev/ops processes). Certs give *basic* architecture grounding — do NOT self-title "Solution Architect." User does NOT want quantifications. The original "Built a Data Mesh…" overclaims sole ownership and must be hedged.
|
||||
|
||||
1. **Fix SW-7 verb discipline + surface data-layer architecture (the accuracy fix and the on-title win, combined).** — `~+1.2`
|
||||
- Current: `Built a \textbf{Data Mesh} of governed data products with metadata management on \textbf{AWS} (Glue, Athena, CloudFormation, CI/CD), the data foundation that AI and \textbf{agentic workflows} query for grounded retrieval.`
|
||||
- **Proposed (216 chars, fits 2L):** `Helped move Swisscom from legacy Teradata to a cloud \textbf{Data Mesh} on \textbf{AWS}; modelled and built governed \textbf{data products} and onboarded source systems onto the foundation AI and \textbf{agentic workflows} query for grounded retrieval.`
|
||||
- *Why:* "Helped move" hedges the company-wide migration honestly; "modelled / built / onboarded" are full-ownership for work he genuinely did. The data **modelling/design** language is real **data-layer architecture** — the honest way to hit the JD's "architectural experience across the data layer" without claiming an architect title.
|
||||
- Summary opener tweak: `Software engineer with 11+ years…` → `Software and AI engineer with 11+ years…`; and `At Swisscom I build the AWS Data Mesh and governed data products…` → `At Swisscom I design and build governed data products on the company's AWS Data Mesh…` (same hedge, preserves page fill). Keep "AWS Solutions Architect" cert mention (honest architecture signal).
|
||||
- **Do NOT** add "Solution Architect" to the tagline/summary self-label — overclaims per user (certs = basic architecture grounding only).
|
||||
2. **Add "orchestration" + "reference architecture / solution patterns" where truthful.** — `~+0.8`
|
||||
- Skills (Agentic line or Cloud line): add `orchestration` (K8s/pipeline + agent-workflow orchestration is real).
|
||||
- The governed-data-product / ODP work can honestly be described with "reference architecture / solution patterns" language in the skills section (it *is* a governed reference pattern Dennis modelled against). Keep honest.
|
||||
- *Why:* JD names both; absent verbatim now and cheap to add truthfully.
|
||||
|
||||
~~3. Inject quantified business-impact metric~~ — **REMOVED per user (does not want quantifications).** The "measurable business impact" gap is therefore an accepted limitation; achievable ceiling drops ~1 pt accordingly (now ~80.5 → ~81 max with Tier 1).
|
||||
|
||||
### Tier 2 (MEDIUM — optional; ~+1 pt)
|
||||
1. **Fix 3 participial bullet endings (AI-fingerprint).** — `~+0.4`
|
||||
- B4 "…enabling serverless data processing for ML and analytics workloads" / B8 "…providing centralized observability for 24/7 semiconductor manufacturing infrastructure" / B10 "…supplying semiconductor analysis teams with structured access…". Restructure so each ends on a concrete object/result rather than an `-ing` trailer. Pattern repeated 3× is a detectable marker.
|
||||
2. **Add "document understanding" to multimodal skill line** if any doc-parsing work is truthful — `~+0.3`. Otherwise skip.
|
||||
3. **Tighten CL to ≤300 words** (currently ~313; industry target 250–300) — `~+0.2`.
|
||||
|
||||
### Tier 3 (COSMETIC — skip)
|
||||
1. Page-2 underfill (~30% empty): could add a reserve bullet, but content is already complete and honest; not worth padding.
|
||||
2. Promote iSAQB CPSA up the cert order (minor; Tier 1 tagline change already surfaces architecture).
|
||||
|
||||
### Verdict
|
||||
**Apply Tier 1.** Tier 1 is fully truthful, on-title, and the highest-leverage set available to a reach application — it raises the recruiter/HR pass-through where this resume is most likely to die. Tier 2 is worth the AI-fingerprint fix if editing anyway. Tier 3 skip. **No accuracy/provenance violations found.** The structural ceiling (named frameworks, Azure, people-management) is real and correctly *not* faked.
|
||||
|
||||
---
|
||||
|
||||
## Cover Letter Critique
|
||||
|
||||
**Institution type:** Industry (major energy company, applied AI/architecture org).
|
||||
|
||||
**6A — Anti-patterns:** ✓ Opens with a specific Equinor fact (Prevent, 520 models, $130M), not "I am writing to express interest." ✓ No CV-bullet rehash. ✓ Names Prevent + Omnia. ✓ Clear "why this role." ✓ Strongest qualification (Bosch production ML) in P1. ✓ No apologetic/defensive language — the "I will be candid" line is confident, not apologetic. ✓ Active close ("welcome a conversation about where I could contribute first"). **Pass.**
|
||||
|
||||
**6B — Tailoring:** ✓ Names Prevent + Omnia (their tech). ✓ Supplements resume with JD terms (rotating equipment, safety-critical, agentic layer, zero-harm). ✓ References mission (energy transition) + culture (zero-harm). ✓ Proposes connection (production-reliability + responsible-AI discipline → "systems you can trust"). **Pass.**
|
||||
|
||||
**6C — Industry checks:** ✓ Business-value translation ($130M, "no maintenance window, a wrong call costs yield"). ✓ "Why this" addressed positively. ✓ Jargon HR-safe. **Pass.**
|
||||
|
||||
**6D — CL ATS:** Supplementary JD terms present (agentic, grounded retrieval, MCP, GDPR, EU AI Act, responsible AI, CI/CD, rollback, orchestration-adjacent). ~7 high-value terms — good.
|
||||
|
||||
**6E — Structural:** Word count ~313 (target 250–300 — slightly long, Tier 2 trim). Tone results-driven ✓. Sentence-length variety good ✓. 0 em-dashes ✓. Domain pivot leads with methodology, not apology ✓. Quantified claims: 520 models, $130M, 300mm, year in Bergen — adequate.
|
||||
|
||||
**6F — Package cohesion:** ✓ Resume stands alone (CL deleted, resume still earns its ~same read). ✓ Every CL claim traces to a resume bullet (Data Mesh/Omnia → SW-7; Bosch → BS-1; LiteLLM/GPTs → SW-GenAI; Security Champion → SW-5; K8s/rollback → SW-3). ✓ No contradictions in dates/metrics/framing. ✓ Complements (adds Prevent↔Bosch narrative, Norway motivation, honest agentic-pivot framing) rather than repeating. ✓ Resume+CL = 3pp budget. **Strong cohesion.**
|
||||
|
||||
**6G — AI fingerprint scan (12-item):** No Tier 1 banned words; no banned phrases; 0 em-dashes in CL (0 in resume output — the 17 `---` hits are LaTeX comment dividers, not prose); CL opener company-specific; sentence length varied; no metaphorical landscape/journey/realm; no banned adverbs. **Only finding:** the 3 resume bullet `-ing` trailer endings (Tier 2 above). CL clean.
|
||||
|
||||
---
|
||||
|
||||
## Interview Bridge Points
|
||||
|
||||
| Resume Topic | Equinor Equivalent | Opening Line |
|
||||
|---|---|---|
|
||||
| Bosch ML inference in 24/7 fab | Prevent / always-on industrial ML | "The zero-downtime discipline I ran against 300mm wafer lines is the same regime Prevent operates in — no maintenance window, a wrong call costs yield." |
|
||||
| AWS Data Mesh / governed data products | Omnia + grounded retrieval for agents | "I built the governed, discoverable data layer agents ground against — the same role Omnia plays for you, just on AWS." |
|
||||
| LiteLLM gateway + custom GPTs | Structured LLM integration w/ enterprise APIs | "I stood up a multi-provider LLM gateway and grounded GPTs — the integration plumbing under any agent; the agent-framework orchestration layer is where I'd ramp fast." |
|
||||
| Security Champion + GDPR/governance | Responsible AI / EU AI Act / policy-as-code | "Privacy-by-design and risk monitoring are already how I work — that's the substance behind bounded autonomy and safe fallback, not a checkbox." |
|
||||
| K8s + CI/CD + rollback | Engineering quality, reliability, safe rollout | "Containerized delivery with safe rollback is my default — that's what turns an agent prototype into something you can trust in production." |
|
||||
| iSAQB CPSA + AWS SAA | Architecture across data/model/app layers | "I hold a formal software-architecture certification and design across the data and application layers — I reason in trade-offs, scalability, and risk." |
|
||||
| Year at Vizrt, Bergen | Norway fit / relocation | "I've already lived and shipped in Norway — Bergen, broadcast-scale backend — so relocating back and the culture fit aren't a leap." |
|
||||
|
||||
---
|
||||
|
||||
*End of critique. Pass 1 — score 77.5/100. Honest-stretch reach application; framing well-executed, structural fit ceiling ~83.*
|
||||
@@ -0,0 +1,44 @@
|
||||
\documentclass[11pt,a4paper,roman]{moderncv}
|
||||
\usepackage[english]{babel}
|
||||
\moderncvstyle{classic}
|
||||
\moderncvcolor{green}
|
||||
\usepackage[utf8]{inputenc}
|
||||
\usepackage[T1]{fontenc}
|
||||
\usepackage{lmodern}
|
||||
\usepackage{ragged2e}
|
||||
\usepackage[scale=0.79]{geometry}
|
||||
\usepackage[version=4,arrows=pgf-filled]{mhchem}
|
||||
\renewcommand*{\makeletterclosing}{\par\vspace{2ex}\closingname\par}
|
||||
|
||||
% ========== CONTACT ==========
|
||||
\name{Dennis}{Thiessen, M.Eng.}
|
||||
\address{Bern, Switzerland}{German citizen $\vert$ Open to relocation to Norway}
|
||||
\phone[mobile]{+41 795 955 585}
|
||||
\email{dennis@thiessen.io}
|
||||
\social[linkedin]{dennis-thiessen}
|
||||
% =============================
|
||||
|
||||
\begin{document}
|
||||
|
||||
\recipient{Equinor ASA}{AI \& ML Engineering\\Manager / AI Architect -- Agentic Systems (JR106747)\\Stavanger, Norway}
|
||||
\date{\today}
|
||||
\opening{Dear Hiring Team,}
|
||||
\makelettertitle
|
||||
|
||||
\begin{justify}
|
||||
Equinor's Prevent system runs over 520 machine-learning models in production against rotating equipment, saving nearly \$130 million last year. That always-on industrial ML, where there is no maintenance window and a wrong call costs yield, is the regime I ran at Bosch's semiconductor fab in Dresden: I containerized image-based defect classification and ran it around the clock against 300mm wafer lines. Equinor already runs ML at scale on safety-critical assets; the agentic layer is the next foundation, built with the same discipline.
|
||||
|
||||
At Swisscom I am a Staff Data, Analytics and AI Engineer, and I build the data layer agents depend on: governed data products on the company's AWS Data Mesh, the foundation that grounded retrieval and tool access query, much as Omnia does for you. I own them from build through production on Kubernetes with CI/CD and safe rollback, and I take AI from concept to production, not just to a demo.
|
||||
|
||||
On the AI side I have built structured LLM integrations: a self-hosted, multi-provider LiteLLM gateway, plus custom GPTs grounded in internal knowledge for prompt design and retrieval, with agentic developer tooling and MCP-based tool access. As Security Champion I own DevSecOps, risk monitoring and data governance, with privacy-by-design and GDPR practice that map onto responsible AI, the EU AI Act, and safe execution. I will be candid: the agentic layer is new for nearly everyone, and what I bring is the production reliability and responsible-AI discipline that turns prototypes into systems you can trust.
|
||||
|
||||
The energy transition is work I want to be part of, and Norway is not new to me: I spent a year in Bergen, speak basic Norwegian, and am ready to relocate back. Your zero-harm culture fits how I already work. I would welcome a conversation about where I could contribute first.
|
||||
\end{justify}
|
||||
|
||||
\vspace{0.3cm}
|
||||
{Sincerely,\\[2ex]
|
||||
Dennis Thiessen, M.Eng.\\
|
||||
Staff Data, Analytics \& AI Engineer\\
|
||||
Swisscom (Schweiz) AG}
|
||||
|
||||
\end{document}
|
||||
@@ -0,0 +1,167 @@
|
||||
\documentclass{resume}
|
||||
\usepackage{hyperref}
|
||||
\usepackage{enumitem}
|
||||
\usepackage{fontawesome}
|
||||
\usepackage{tikz}
|
||||
\usepackage{graphicx}
|
||||
\hypersetup{
|
||||
colorlinks = true,
|
||||
linkcolor = [rgb]{0.9,0.4,0.4},
|
||||
anchorcolor = [rgb]{0.9,0.4,0.4},
|
||||
citecolor = [rgb]{0.4,0.4,0.4},
|
||||
filecolor = [rgb]{0.4,0.4,0.4},
|
||||
urlcolor = [rgb]{0.0,0.0,0.99},
|
||||
}
|
||||
\usepackage{xcolor}
|
||||
\usepackage[utf8]{inputenc}
|
||||
\usepackage[T1]{fontenc}
|
||||
\usepackage{lmodern}
|
||||
\usepackage[version=4,arrows=pgf-filled]{mhchem}
|
||||
\usepackage[includefoot,left=0.5in,top=0.5in,right=0.5in,bottom=0.2in,textwidth=7.5in,textheight=10.8in]{geometry}
|
||||
\usepackage{fancyhdr}
|
||||
\pagestyle{fancy}
|
||||
\fancyhf{}
|
||||
\renewcommand{\headrulewidth}{0pt}
|
||||
\fancyfoot[R]{\hfill \thepage/\pageref{LastPage}}
|
||||
\newcommand{\tab}[1]{\hspace{.2667\textwidth}\rlap{#1}}
|
||||
\newcommand{\itab}[1]{\hspace{0em}\rlap{#1}}
|
||||
|
||||
%----------------------------------------------------------------------------------------
|
||||
% HEADER
|
||||
%----------------------------------------------------------------------------------------
|
||||
\name{Dennis Thiessen, M.Eng.}
|
||||
\address{\href{https://linkedin.com/in/dennis-thiessen}{LinkedIn}}
|
||||
\address{dennis@thiessen.io \\ +41 795 955 585}
|
||||
\address{Bern, Switzerland $\vert$ German citizen $\vert$ Open to relocation to Norway}
|
||||
\address{{AI/ML Engineer $\vert$ Agentic Data Foundations $\cdot$ LLM Integration $\cdot$ MLOps $\vert$ Python $\cdot$ Kubernetes $\cdot$ AWS}}
|
||||
|
||||
|
||||
\begin{document}
|
||||
|
||||
\vspace{-0.15cm}
|
||||
|
||||
%----------------------------------------------------------------------------------------
|
||||
% SUMMARY
|
||||
%----------------------------------------------------------------------------------------
|
||||
\begin{rSection}{Summary}
|
||||
Software and AI engineer with 11+ years building and operating production data and AI systems. At Swisscom I design and build governed \textbf{data products} on the company's \textbf{AWS} \textbf{Data Mesh} that AI and \textbf{agentic workflows} query, plus \textbf{custom GPTs} and \textbf{LiteLLM}-routed engineering assistants. Earlier I containerized \textbf{ML inference} into a 24/7 Bosch semiconductor fab (\textbf{Docker}, \textbf{Kubernetes}, Ansible) with zero downtime. \textbf{Python} expert, AWS Solutions Architect, and Security Champion owning \textbf{responsible-AI} and data governance. A year in Bergen, Norway; open to relocating back.
|
||||
\end{rSection}
|
||||
\vspace{-0.15cm}
|
||||
|
||||
%----------------------------------------------------------------------------------------
|
||||
% TECHNICAL SKILLS — Format C, 5 groups (4-4-3-3-3 = 17 lines)
|
||||
%----------------------------------------------------------------------------------------
|
||||
\begin{rSection}{Technical Skills}
|
||||
|
||||
\begin{skillgroup}{Agentic AI, LLM Integration \& MLOps}
|
||||
\skilldash{\textbf{LLM integration}, \textbf{custom GPTs}, \textbf{LiteLLM} (LLM API gateway), prompt design, grounded retrieval, RAG}
|
||||
\skilldash{\textbf{ML inference}, \textbf{model serving}, \textbf{MLOps}, evaluation, orchestration, agentic workflows, MCP tooling}
|
||||
\skilldash{\textbf{Kiro} / spec-driven dev, Copilot, \textbf{PyTorch}, Scikit-learn, image classification, speech recognition, multimodal}
|
||||
\skilldash{Responsible AI, GDPR / EU AI Act, PII handling, policy-as-code, human-in-the-loop, safe fallback and rollback}
|
||||
\end{skillgroup}
|
||||
|
||||
\begin{skillgroup}{Data Foundations \& Engineering}
|
||||
\skilldash{\textbf{Data Mesh}, \textbf{data products}, reference architecture, metadata management, data governance, ETL/ELT design}
|
||||
\skilldash{\textbf{Kafka}, \textbf{Airflow}, \textbf{PySpark} / Apache Spark, Apache Iceberg, Hadoop / ImpalaSQL, stream processing}
|
||||
\skilldash{Teradata DWH, OracleDB, SQL (Oracle, Impala, Teradata, Postgres), SQL performance tuning, data lineage}
|
||||
\skilldash{High-throughput pipelines, real-time event processing, data lakehouse, SLA / on-call ownership, data quality}
|
||||
\end{skillgroup}
|
||||
|
||||
\begin{skillgroup}{Cloud-Native Infrastructure \& Observability}
|
||||
\skilldash{\textbf{AWS} (S3, Glue, Athena/Iceberg, Redshift, Lambda, \textbf{Airflow}, Step Functions, CloudFormation, AWS CLI)}
|
||||
\skilldash{\textbf{Kubernetes}, \textbf{Docker}, Ansible, GitLab CI/CD, Jenkins, Infrastructure as Code, DevSecOps, serverless}
|
||||
\skilldash{ELK Stack (Elasticsearch, Logstash, Kibana), \textbf{Grafana}, \textbf{Prometheus}, Loki, log aggregation, alerting}
|
||||
\end{skillgroup}
|
||||
|
||||
\begin{skillgroup}{Programming \& APIs}
|
||||
\skilldash{\textbf{Python} (expert), \textbf{Java}, SQL, JavaScript/TypeScript, C\#, C++ (legacy), Bash, Git}
|
||||
\skilldash{FastAPI / Flask, REST API design, Express.js microservices, Entity Framework / .NET, Spring Boot, Apache Camel}
|
||||
\skilldash{Pandas, NumPy, SQLAlchemy, pytest, Jupyter, software design patterns, code review, Agile / Scrum}
|
||||
\end{skillgroup}
|
||||
|
||||
\begin{skillgroup}{Domain, Leadership \& Responsible AI}
|
||||
\skilldash{Enterprise data platforms (telecom), \textbf{semiconductor manufacturing} / Industry 4.0, maritime \& broadcast systems}
|
||||
\skilldash{Technical leadership, mentoring, stakeholder alignment, ambiguity / strategy-to-delivery, cross-functional work}
|
||||
\skilldash{Security-by-design, \textbf{DevSecOps}, risk monitoring, data governance, privacy / GDPR, responsible-AI guardrails}
|
||||
\end{skillgroup}
|
||||
|
||||
\end{rSection}
|
||||
\vspace{-0.15cm}
|
||||
|
||||
%----------------------------------------------------------------------------------------
|
||||
% PROFESSIONAL EXPERIENCE
|
||||
%----------------------------------------------------------------------------------------
|
||||
\begin{rSection}{Professional Experience}
|
||||
|
||||
% --- Swisscom (Oct 2023 -- Present) — 6 bullets: SW-7, SW-GenAI, SW-5, SW-1, SW-3, SW-2 ---
|
||||
\begin{rSubsection}{Agentic-AI Data Foundations, LLM Integration \& Responsible-AI Engineering}{\textcolor{black!60}{Oct 2023 -- Present}}{Staff Data, Analytics \& AI Engineer, Swisscom (Schweiz) AG}{Bern, Switzerland}
|
||||
\item Helped move Swisscom off legacy Teradata to a cloud \textbf{Data Mesh} on \textbf{AWS}; modelled and built governed data products and onboarded source systems that \textbf{agentic workflows} query for grounded retrieval.
|
||||
\item Built \textbf{custom GPTs} and \textbf{LiteLLM}-routed assistants (LLM API gateway with model routing) that automate engineering workflows like code review, documentation and pipeline triage on a spec-driven \textbf{Kiro} toolchain.
|
||||
\item Hold Swisscom's \textbf{Security Champion} role (2025/26), owning DevSecOps, risk monitoring and data governance, with security-by-design and GDPR compliance that carry directly into \textbf{responsible-AI} guardrails.
|
||||
\item Migrated legacy Teradata/Oracle ETL stack to \textbf{AWS} cloud-native (S3, Glue, \textbf{Airflow}, Athena/Iceberg, Redshift, CloudFormation IaC) for serverless data processing across ML and analytics workloads.
|
||||
\item Deploy and operate \textbf{Python} services on \textbf{Kubernetes} with GitLab CI/CD, owning containerized delivery from build and test through production rollout and rollback across multiple data products and DevOps teams.
|
||||
\item Owned Fulfillment and Product Analysis ETL pipelines (Oracle, \textbf{Kafka} to Teradata in \textbf{Python}) as Component Owner; enforced data governance and SLA compliance for business-critical telecom-scale production flows.
|
||||
\end{rSubsection}
|
||||
|
||||
% --- Bosch (Feb 2020 -- Dec 2022) — 4 bullets: BS-1, BS-4, BS-3, BS-2 ---
|
||||
\begin{rSubsection}{Production ML from Concept to Deployment in 24/7 Manufacturing}{\textcolor{black!60}{Feb 2020 -- Dec 2022}}{(Senior) Data \& ML Engineer, Robert Bosch Semiconductor Manufacturing}{Dresden, Germany}
|
||||
\item Designed \textbf{ML inference} infrastructure (\textbf{Docker}, \textbf{Kubernetes}, Ansible) for Bosch's 24/7 semiconductor fab, automating image-based defect classification across 300mm wafer production lines without downtime.
|
||||
\item Built anomaly detection PoC: ELK Stack with \textbf{Kafka} (\textbf{Docker}), \textbf{Grafana}, \textbf{Prometheus} and Loki for centralized log aggregation and observability across 24/7 semiconductor manufacturing infrastructure.
|
||||
\item Served as Application Owner for the semiconductor analytics suite and upstream data pipelines, defining SLOs, managing vendors, and delivering user training and documentation across fab operations teams.
|
||||
\item Built data services in \textbf{Python}, Java and C\# over OracleDB and Hadoop/ImpalaSQL that gave semiconductor analysis teams reliable, structured access to defect management and process optimization data.
|
||||
\end{rSubsection}
|
||||
|
||||
% --- Fraunhofer (Sep 2018 -- Oct 2019) — 3 bullets: FC-2, FC-3, FC-1 ---
|
||||
\begin{rSubsection}{Applied NLP, Speech Recognition \& Microservice Engineering}{\textcolor{black!60}{Sep 2018 -- Oct 2019}}{Research Software Engineer, Fraunhofer-Center for Maritime Logistics CML}{Hamburg, Germany}
|
||||
\item Contributed \textbf{ML and NLP} components to ARTUS, a Fraunhofer research project building automatic \textbf{speech-to-text} transcription of distress calls for sea-rescue operations in a safety-critical maritime domain.
|
||||
\item Built microservices (Express.js, \textbf{Docker}, SQLite) for MISSION, a Fraunhofer platform enabling maritime data exchange and tool access across logistics stakeholders including ports, operators and research partners.
|
||||
\item Set up the team's first Jenkins CI/CD pipeline with quality gates independently, and developed SCEDAS crew-scheduling software (C\#, .NET, MS SQL Server, Entity Framework) with added test coverage.
|
||||
\end{rSubsection}
|
||||
|
||||
% --- Vizrt (Jul 2017 -- May 2018) — 2 bullets: VZ-1, VZ-2 ---
|
||||
\begin{rSubsection}{Distributed Real-Time Backend Engineering at Broadcast Scale}{\textcolor{black!60}{Jul 2017 -- May 2018}}{DevOps Engineer, Vizrt}{Bergen, Norway}
|
||||
\item Built distributed real-time video transcoding backend components in \textbf{Python} (with legacy C++ modules) for Vizrt's broadcast platform, serving global media customers including CNN, BBC and Al Jazeera.
|
||||
\item Built automated integration and unit test suite for A/V streaming (\textbf{Python}) and integrated quality gates into CI/CD, which shortened the feedback loop for new features and raised release quality.
|
||||
\end{rSubsection}
|
||||
|
||||
% --- Generali (May 2015 -- Jun 2017) — 2 bullets: GN-1, GN-3 ---
|
||||
\begin{rSubsection}{Technical Leadership, Test Automation \& Java Backend}{\textcolor{black!60}{May 2015 -- Jun 2017}}{IT Consultant, Generali Deutschland Informatik Services}{Hamburg, Germany}
|
||||
\item Introduced BDD test automation at Generali (Serenity-BDD, Selenium, JBehave), running the initial PoC and taking technical ownership, then trained engineers and presented the methodology to the Java Community.
|
||||
\item Developed Java/J2EE features for the PIA-Postkorb workflow portal, migrated WebServices to the XLDeploy process, and contributed to an Apache Camel / Spring Boot dispatcher integration PoC.
|
||||
\end{rSubsection}
|
||||
|
||||
|
||||
\end{rSection}
|
||||
\vspace{-0.15cm}
|
||||
|
||||
%----------------------------------------------------------------------------------------
|
||||
% EDUCATION — FIXED
|
||||
%----------------------------------------------------------------------------------------
|
||||
\begin{rSection}{Education}
|
||||
{M.Eng.\ Computer Aided Engineering (Software Design \& Engineering)} \hfill {\textcolor{black!60}{Oct 2010 -- Jul 2013}}\\
|
||||
{Universit\"at der Bundeswehr M\"unchen}; thesis at Tongji University, Shanghai \hfill Thesis Grade: \textbf{1.0}\\
|
||||
{\small Thesis: \textit{Development of a Web-Based Remote Fault Diagnosis System} (Neural Networks, PSO, Fuzzy Logic)}
|
||||
|
||||
{B.Eng.\ Information and Telecommunication Technologies} \hfill {\textcolor{black!60}{Oct 2007 -- Sep 2010}}\\
|
||||
{Universit\"at der Bundeswehr M\"unchen}, Munich, Germany
|
||||
\end{rSection}
|
||||
\vspace{-0.15cm}
|
||||
|
||||
%----------------------------------------------------------------------------------------
|
||||
% CERTIFICATIONS — FIXED
|
||||
%----------------------------------------------------------------------------------------
|
||||
\begin{rSection2}{Certifications}
|
||||
\item \textbf{AWS Certified Solutions Architect -- Associate}, Amazon Web Services (2024, active until Sep 2027).
|
||||
\item \textbf{Data Engineering with AWS Nanodegree}, Udacity (2026). AWS data pipeline architecture.
|
||||
\item \textbf{IBM AI Engineering Specialization}, Coursera. Deep learning, TensorFlow, Keras, Apache Spark ML.
|
||||
\item \textbf{iSAQB CPSA -- Foundation Level}, iSAQB (2016). Certified Professional for Software Architecture.
|
||||
\item \textbf{AI for Trading Nanodegree}, Udacity / WorldQuant (2021). Quantitative ML, time-series analysis.
|
||||
\item \textbf{ITIL Foundation Certificate in IT Service Management}, PEOPLECERT / AXELOS (2016).
|
||||
\end{rSection2}
|
||||
|
||||
\begin{center}
|
||||
\vspace{0.1cm}
|
||||
\textit{Languages: German (native), English (fluent), Norwegian (basic)}
|
||||
\end{center}
|
||||
|
||||
\end{document}
|
||||
@@ -0,0 +1,110 @@
|
||||
Manager / AI Architect – Agentic systems
|
||||
Apply
|
||||
|
||||
locations
|
||||
Stavanger, Norway
|
||||
Oslo, Norway
|
||||
Rotvoll, Norway
|
||||
Sandsli, Norway
|
||||
|
||||
posted on
|
||||
Posted 5 Days Ago
|
||||
|
||||
job requisition id
|
||||
JR106747
|
||||
|
||||
Important! To make sure your application is considered, please submit it before the end of the day on (dd.mm.yyyy):
|
||||
05.06.2026
|
||||
|
||||
We encourage candidates to apply as soon as possible.
|
||||
|
||||
What does the job involve?
|
||||
Shape how Equinor designs and scales agentic AI solutions—working at the intersection of architecture, engineering, and responsible AI.
|
||||
|
||||
Equinor is building the foundation for enterprise-scale agentic AI, and this role offers a rare opportunity to play a key role in that journey. You will architect solutions, make key design decisions, guide delivery with AI and ML engineering teams, and ship production systems that automate workflows and sharpen decisions across multiple business areas.
|
||||
|
||||
What will my tasks be?
|
||||
|
||||
Within this position, your key tasks will be to:
|
||||
|
||||
Shape and apply reference architecture for agentic systems, translating standards, design principles, and guardrails into practical solution patterns across Equinor.
|
||||
|
||||
Architect and deliver production agents: orchestration, grounded retrieval, structured LLM integrations with enterprise APIs, MCP-based tool/data access, and multimodal document understanding.
|
||||
|
||||
Drive solution strategy, technology choices, and architectural blueprints for key use cases; align stakeholders, engineering teams, and partners; and provide technical leadership from concept through scaled deployment.
|
||||
|
||||
Embed safety, compliance, and privacy by design; align with GDPR and the EU AI Act; enforce policy as code and safe tool execution; and manage uncertainty in non-deterministic systems by surfacing confidence, bounding autonomy, routing to human oversight, and providing safe fallback and rollback paths.
|
||||
|
||||
Raise the bar on engineering quality and long-term capability by improving performance, reliability, and cost efficiency, while mentoring peers and building reusable foundations for future AI solutions.
|
||||
|
||||
Here's what we expect from you:
|
||||
|
||||
At Equinor, there are some overall qualities we regard as essential. We want you to identify with the values that guide our decisions and help us succeed and grow: open, collaborative, courageous and caring. We expect you to make safety your priority and to contribute to our zero-harm culture. And for this specific position, we are also looking for:
|
||||
|
||||
Required qualifications
|
||||
|
||||
Master’s or PhD in Computer Science, Data Science, Machine Learning, Linguistics, or related field.
|
||||
|
||||
Strong architectural experience across data, model, and application layers, with sound judgment on trade-offs, scalability, risk, and compliance in enterprise AI systems.
|
||||
|
||||
Proven ability to navigate ambiguity, set technical direction within a broader architecture, align stakeholders, and convert strategy into delivery.
|
||||
|
||||
Hands-on with modern LLMs and agent frameworks (e.g., LangGraph, AutoGen, LangChain/LlamaIndex, Semantic Kernel).
|
||||
|
||||
NLP and generative AI expertise, including prompt design, RAG architectures, model evaluation, and practical experience with major LLM providers and open-source models.
|
||||
|
||||
Solid Python and software engineering fundamentals (testing, CI/CD, version control).
|
||||
|
||||
Track record of delivering AI solutions from concept to production, with measurable business impact.
|
||||
|
||||
Preferred qualifications
|
||||
|
||||
Technical leadership: mentoring, communities, publishing, speaking, or open-source contributions.
|
||||
|
||||
Multimodal AI: document and image understanding, diagram Q&A, speech-to-text.
|
||||
|
||||
Responsible AI: PII handling, red-teaming, content moderation, risk assessment, regulatory compliance.
|
||||
|
||||
Containers and cloud: Docker, Kubernetes; Azure (Azure ML, AKS, Azure OpenAI, storage, networking).
|
||||
|
||||
Integration: APIs, events/messaging, standardised data and tool access via MCP.
|
||||
|
||||
Why join us?
|
||||
|
||||
If you are motivated by architecting practical AI solutions, working on technically demanding challenges, and helping scale responsible agentic AI in a major energy company, we would love to hear from you.
|
||||
|
||||
What can we offer you?
|
||||
|
||||
We want you to have a rewarding and fulfilling work life. That’s why we offer:
|
||||
|
||||
Not just a job - a career
|
||||
|
||||
In Equinor, your development begins on day one. You will build your competence through a wide range of learning activities while being empowered to build your career across multiple disciplines and geographies. Our internal job market allows a wide range of opportunities for development and growth within your own field, or even in other areas you find interesting and relevant.
|
||||
|
||||
Attractive rewards
|
||||
|
||||
We give you a comprehensive benefits package with a competitive salary, global parental leave, bonus scheme and pension plan.
|
||||
|
||||
Wellness and work-life balance
|
||||
|
||||
We care about and prioritise our employees’ well-being. We know that for you to be the best version of yourself in the workplace, being able to collect your children, attend a class or simply enjoy social time can be invaluable. That’s why we encourage you to make use of our flexible work arrangements wherever possible.
|
||||
|
||||
An inclusive culture
|
||||
|
||||
We believe embracing our differences makes us stronger. For us, true inclusion means being able to bring your whole self to work, and for you and everyone else to feel accepted and valued.
|
||||
|
||||
Equal opportunities for everyone
|
||||
|
||||
Equinor is an equal-opportunity employer. We make all employment decisions, which include hiring, promotion, transfer, demotion, termination, and training, without regard to race, colour, religion, sex, sexual orientation, gender identity, national origin, age, disability, marital status, parental status, veteran status, or any other protected status.
|
||||
|
||||
As part of this commitment, reasonable adjustments will be made during the recruitment process for candidates with disabilities or long-term health conditions. If you have any specific requirements, please clarify this in your application and our team will be in contact to see how we can support your needs.
|
||||
|
||||
We also believe everyone should be paid fairly and consistently for their contribution to our collective success. To ensure fairness and transparency, positions at Equinor are evaluated using our global job architecture based on the position’s responsibilities, complexity, and impact, and regularly reviewed to ensure consistency and alignment across the organisation.
|
||||
|
||||
Important notes about the application process
|
||||
|
||||
We expect you to openly offer all relevant information about yourself during the recruitment process. Background checks are performed on all final candidates, and all permanent and temporary hires will be screened using relevant sanctions lists to ensure compliance with sanctions laws. When applying for a job in Norway you will be asked for information on affiliation to high-risk countries for a security assessment.
|
||||
|
||||
About Equinor
|
||||
|
||||
Equinor is an international energy company headquartered in Norway, energising the lives of 170 million people worldwide. Our ambition is to be a leading company in the energy transition and achieve net zero by 2050. Our task is enormous: supplying the world with the energy it needs, while lowering emissions to the atmosphere. To achieve it, we are looking for like-minded people to join our team of 25,000 colleagues working in more than 20 countries. We’re up for the challenge. Are you?
|
||||
@@ -0,0 +1,199 @@
|
||||
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
||||
% Medium Length Professional CV - RESUME CLASS FILE
|
||||
%
|
||||
% This template has been downloaded from:
|
||||
% http://www.LaTeXTemplates.com
|
||||
%
|
||||
% This class file defines the structure and design of the template.
|
||||
%
|
||||
% Original header:
|
||||
% Copyright (C) 2010 by Trey Hunner
|
||||
%
|
||||
% Copying and distribution of this file, with or without modification,
|
||||
% are permitted in any medium without royalty provided the copyright
|
||||
% notice and this notice are preserved. This file is offered as-is,
|
||||
% without any warranty.
|
||||
%
|
||||
% Created by Trey Hunner and modified by www.LaTeXTemplates.com
|
||||
%
|
||||
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
||||
|
||||
\ProvidesClass{resume}[2018/09/25 v1.0 Resume class]
|
||||
|
||||
\LoadClass[10pt, a4paper]{article} % Font size and paper type
|
||||
\usepackage{lastpage}
|
||||
\usepackage[parfill]{parskip} % Remove paragraph indentation
|
||||
\usepackage{array} % Required for boldface (\bf and \bfseries) tabular columns
|
||||
\usepackage{ifthen} % Required for ifthenelse statements
|
||||
\usepackage{enumitem}
|
||||
\pagestyle{empty} % Suppress page numbers
|
||||
|
||||
%----------------------------------------------------------------------------------------
|
||||
% HEADINGS COMMANDS: Commands for printing name and address
|
||||
%----------------------------------------------------------------------------------------
|
||||
|
||||
\def \name#1{\def\@name{#1}} % Defines the \name command to set name
|
||||
\def \@name {} % Sets \@name to empty by default
|
||||
|
||||
\def \addressSep {$|$} % Set default address separator to a diamond
|
||||
|
||||
% One, two or three address lines can be specified
|
||||
\let \@addressone \relax
|
||||
\let \@addresstwo \relax
|
||||
\let \@addressthree \relax
|
||||
\let \@addressfour \relax
|
||||
|
||||
% \address command can be used to set the first, second, and third address (last 2 optional)
|
||||
\def \address #1{
|
||||
\@ifundefined{@addresstwo}{
|
||||
\def \@addresstwo {#1}
|
||||
}{
|
||||
\@ifundefined{@addressthree}{
|
||||
\def \@addressthree {#1}
|
||||
}{
|
||||
\@ifundefined{@addressfour}{
|
||||
\def \@addressfour {#1}
|
||||
} {\def \@addressone {#1}
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
% \printaddress is used to style an address line (given as input)
|
||||
\def \printaddress #1{
|
||||
\begingroup
|
||||
\def \\ {\addressSep\ }
|
||||
{#1}
|
||||
% \centerline{#1}
|
||||
\endgroup
|
||||
\par
|
||||
% \addressskip
|
||||
}
|
||||
|
||||
% \printname is used to print the name as a page header
|
||||
\def \printname {
|
||||
\begingroup
|
||||
% \MakeUppercase
|
||||
{\namesize\bf \@name} \hfil
|
||||
% \hfil{\MakeUppercase{\namesize\bf \@name}}\hfil
|
||||
\nameskip\break
|
||||
\endgroup
|
||||
}
|
||||
|
||||
%----------------------------------------------------------------------------------------
|
||||
% PRINT THE HEADING LINES
|
||||
%----------------------------------------------------------------------------------------
|
||||
|
||||
\let\ori@document=\document
|
||||
\renewcommand{\document}{
|
||||
\ori@document % Begin document
|
||||
% \begin{center}
|
||||
\printname % Print the name specified with \name
|
||||
\@ifundefined{@addressone}{}{ % Print the first address if specified
|
||||
\printaddress{\@addressone}}
|
||||
\@ifundefined{@addresstwo}{}{ % Print the second address if specified
|
||||
\printaddress{\@addresstwo}}
|
||||
\@ifundefined{@addressthree}{}{ % Print the third address if specified
|
||||
\printaddress{\@addressthree}}
|
||||
\@ifundefined{@addressfour}{}{ % Print the third address if specified
|
||||
\printaddress{\@addressfour}}
|
||||
|
||||
% \end{center}
|
||||
}
|
||||
|
||||
%----------------------------------------------------------------------------------------
|
||||
% SECTION FORMATTING
|
||||
%----------------------------------------------------------------------------------------
|
||||
|
||||
% Defines the rSection environment for the large sections within the CV
|
||||
\newenvironment{rSection}[1]{ % 1 input argument - section name
|
||||
\sectionskip
|
||||
{\bf #1}
|
||||
% \MakeUppercase{\bf #1} % Section title
|
||||
\sectionlineskip
|
||||
\hrule % Horizontal line
|
||||
\begin{list}{}{ % List for each individual item in the section
|
||||
\setlength{\leftmargin}{0.50em} % Margin within the section
|
||||
}
|
||||
\item[]
|
||||
}{
|
||||
\end{list}
|
||||
}
|
||||
|
||||
\newenvironment{rSection2}[1]{ % 1 input argument - section name
|
||||
\sectionskip
|
||||
{\bf #1} % Section title
|
||||
\sectionlineskip
|
||||
\hrule % Horizontal line
|
||||
\medskip
|
||||
\begin{list}{$\bullet$}{\setlength{\leftmargin}{1.5em}}
|
||||
\itemsep -0.3em \vspace{-0.5em} % Compress items in list together for aesthetics
|
||||
}{
|
||||
\end{list}
|
||||
\vspace{0.5em}
|
||||
}
|
||||
|
||||
\newenvironment{rSection3}[1]{ % 1 input argument - section name
|
||||
\sectionskip
|
||||
{\bf #1} % Section title
|
||||
\sectionlineskip
|
||||
\hrule % Horizontal line
|
||||
\medskip
|
||||
\begin{enumerate}[]{\setlength{\leftmargin}{1.5em}}
|
||||
\itemsep -0.3em \vspace{-0.5em} % Compress items in list together for aesthetics
|
||||
}{
|
||||
\end{enumerate}
|
||||
\vspace{0.5em}
|
||||
}
|
||||
%----------------------------------------------------------------------------------------
|
||||
% WORK EXPERIENCE FORMATTING
|
||||
%----------------------------------------------------------------------------------------
|
||||
|
||||
\newenvironment{rSubsection}[4]{ % 4 input arguments - company name, year(s) employed, job title and location
|
||||
{\bf #1} \hfill {#2} % Bold company name and date on the right
|
||||
\ifthenelse{\equal{#3}{}}{}{ % If the third argument is not specified, don't print the job title and location line
|
||||
\\
|
||||
{\em #3} \quad {\em #4} % Italic job title and location
|
||||
}\smallskip
|
||||
\begin{list}{$\cdot$}{\leftmargin=1.5em} % \cdot used for bullets, no indentation
|
||||
\itemsep -0.2em \vspace{-0.2em} % Compress items in list together for aesthetics
|
||||
}{
|
||||
\end{list}
|
||||
\vspace{0.2 em} % Some space after the list of bullet points
|
||||
}
|
||||
|
||||
|
||||
|
||||
%----------------------------------------------------------------------------------------
|
||||
% FORMAT C SKILLS COMMANDS
|
||||
%----------------------------------------------------------------------------------------
|
||||
|
||||
% Skills group environment: \begin{skillgroup}{Group Name} ... \end{skillgroup}
|
||||
% Renders bold header + indented dash sub-items. Each \skilldash = exactly 1 rendered line.
|
||||
\newenvironment{skillgroup}[1]{%
|
||||
\textbf{#1}\par\nopagebreak%
|
||||
\vspace{-\parskip}%
|
||||
\begin{list}{--}{\leftmargin=0.8em \labelsep=0.3em \itemsep=0pt \topsep=0.1em \parsep=0pt \partopsep=0pt}%
|
||||
}{%
|
||||
\end{list}%
|
||||
\vspace{-\parskip}\vspace{0.45em}%
|
||||
}
|
||||
|
||||
% Single dash sub-item within a skillgroup. Content must fit 1 rendered line.
|
||||
% Char limit: 119 - (0.5 x bold_char_count) at 10pt
|
||||
\newcommand{\skilldash}[1]{\item #1}
|
||||
|
||||
%----------------------------------------------------------------------------------------
|
||||
% EXPERIENCE SUB-THEME COMMAND
|
||||
%----------------------------------------------------------------------------------------
|
||||
|
||||
% Sub-theme underline header within rSubsection
|
||||
\newcommand{\subtheme}[1]{\item[] \underline{#1}}
|
||||
|
||||
% The below commands define the whitespace after certain things in the document - they can be \smallskip, \medskip or \bigskip
|
||||
\def\namesize{\huge} % Size of the name at the top of the document
|
||||
\def\addressskip{\smallskip} % The space between the two address (or phone/email) lines
|
||||
\def\sectionlineskip{\medskip} % The space above the horizontal line for each section
|
||||
\def\nameskip{\medskip} % The space after your name at the top
|
||||
\def\sectionskip{\medskip} % The space after the heading section
|
||||
@@ -0,0 +1,170 @@
|
||||
# Session: Equinor — Manager / AI Architect, Agentic Systems
|
||||
|
||||
## JD Info
|
||||
- **File:** JDs/equinor_ai_manager.txt.txt
|
||||
- **Role:** Manager / AI Architect – Agentic systems
|
||||
- **Company:** Equinor (international energy company, HQ Norway; net-zero-by-2050 ambition; ~25k staff)
|
||||
- **Bundle:** ML / AI Engineer (Tier 2)
|
||||
- **Format:** Resume (2-page, resume.cls) + 1-page cover letter
|
||||
- **Salary/Details:** Norway-based (Stavanger / Oslo / Rotvoll / Sandsli). Apply by 05.06.2026. Comp scheme: competitive salary + bonus + pension. Relocation in scope (user worked 1 yr in Norway, Norwegian basic).
|
||||
- **Strategic note:** HONEST STRETCH. Required agent-framework + GenAI-architecture + management evidence is thin. Position as senior production-AI/MLOps engineer with architecture breadth reaching toward agentic-AI architect — NOT a checkbox match. Accept reach-application odds.
|
||||
|
||||
## JD Analysis
|
||||
### Requirements
|
||||
| # | Requirement | Match | Evidence |
|
||||
|---|-------------|-------|----------|
|
||||
| 1 | Master's/PhD in CS/DS/ML/Linguistics | Direct | M.Eng. Computer Aided Engineering (Software Design & Engineering) |
|
||||
| 2 | Strong architectural experience across data/model/app layers; trade-offs, scalability, risk, compliance | Bridge HIGH | **Data Mesh / data products / metadata mgmt on AWS (SW-7) = data layer for agents**; cloud-native, K8s, ETL ownership; security/compliance ownership; model-layer still weaker |
|
||||
| 3 | Navigate ambiguity, set technical direction, align stakeholders, strategy→delivery | Bridge MED | Staff/Component Owner, B2B stakeholder data products, elected Leadership Cohort, mentoring |
|
||||
| 4 | Hands-on modern LLMs + agent frameworks (LangGraph, AutoGen, LangChain/LlamaIndex, Semantic Kernel) | GAP | LiteLLM gateway + custom GPTs + Kiro (agentic IDE) only. **Never used named frameworks — do NOT list.** |
|
||||
| 5 | NLP + GenAI: prompt design, RAG, model eval, LLM providers + OSS | Bridge LOW | Custom GPTs (prompt/grounding), LiteLLM multi-provider gateway; Fraunhofer NLP/ASR (dated, contributing dev) |
|
||||
| 6 | Solid Python + SWE fundamentals (testing, CI/CD, version control) | Direct | Python primary, GitLab CI/CD, K8s, DevOps lifecycle ownership |
|
||||
| 7 | Track record delivering AI concept→production, measurable business impact | Bridge HIGH | Bosch: ML inference deployed into 24/7 semiconductor fab (zero-downtime production ML) |
|
||||
| P1 | Technical leadership: mentoring, communities, publishing, speaking, OSS | Bridge LOW | Mentoring + Leadership Cohort; no publishing/OSS/speaking |
|
||||
| P2 | Multimodal AI: doc/image understanding, diagram Q&A, speech-to-text | Bridge MED | Bosch image defect classification (image) + Fraunhofer ARTUS speech recognition (speech-to-text) |
|
||||
| P3 | Responsible AI: PII, red-teaming, content moderation, risk, regulatory compliance | Bridge MED | Security Champion (DevSecOps, risk monitoring), data governance, GDPR/privacy-by-design; no red-teaming |
|
||||
| P4 | Containers + cloud: Docker, K8s; Azure (Azure ML, AKS, Azure OpenAI) | Partial | Docker/K8s Direct; **Azure GAP — AWS-heavy, do NOT claim Azure** |
|
||||
| P5 | Integration: APIs, events/messaging, MCP | Bridge MED | Kafka events/messaging (Direct), LiteLLM API gateway; MCP conceptual via Kiro/Claude tooling |
|
||||
|
||||
### ATS Keywords
|
||||
- **AI/ML:** agentic AI, LLM, RAG, prompt design, model evaluation, production ML, ML inference, MLOps, NLP, speech recognition, image classification, multimodal
|
||||
- **Architecture:** reference architecture, solution patterns, orchestration, guardrails, scalability, reliability, cost efficiency
|
||||
- **Responsible AI:** responsible AI, GDPR, EU AI Act, privacy by design, policy as code, risk assessment, PII, human oversight, fallback/rollback
|
||||
- **Tools:** Python, Docker, Kubernetes, CI/CD, GitLab, Kafka, MCP, LLM API gateway (LiteLLM), enterprise APIs
|
||||
- **Soft:** technical leadership, stakeholder alignment, mentoring, concept-to-production, ambiguity, cross-functional
|
||||
|
||||
### Gap Assessment
|
||||
- **Direct:** Master's, Python + SWE/CI-CD, Docker/Kubernetes, events/messaging (Kafka), concept-to-production delivery (industrial ML)
|
||||
- **Bridge:** architecture breadth (data/app/infra), stakeholder/technical leadership, multimodal (image + speech), responsible AI (security/governance/GDPR), MCP/API integration, LLM integration (LiteLLM/custom GPTs)
|
||||
- **Gap (do NOT claim):** named agent frameworks (LangGraph/AutoGen/LangChain/LlamaIndex/Semantic Kernel); Azure (Azure ML/AKS/Azure OpenAI); production RAG + formal model evaluation; formal people-management; red-teaming/content moderation
|
||||
|
||||
## Company Context
|
||||
- **Mission:** International energy company, HQ Norway; leading the energy transition, net zero by 2050; energising ~170M people.
|
||||
- **This role:** Build the foundation for enterprise-scale agentic AI — shape reference architecture, architect/deliver production agents (orchestration, grounded retrieval, MCP tool access, multimodal doc understanding), embed responsible AI (GDPR/EU AI Act, policy-as-code, bounded autonomy, human oversight, safe fallback/rollback), raise engineering quality/reliability/cost, mentor peers.
|
||||
- **Culture:** Values — open, collaborative, courageous, caring; safety-first / zero-harm culture. Norway-based, strong work-life balance, internal mobility.
|
||||
- **Tech reality (web research):** Omnia data platform on **Azure**; EurekaML (Azure ML/Synapse/Cosmos) cut model deploy 1–2 wks → 1 day; **Prevent: 520+ ML models in production**, millions of predictions/day, detecting rotating-equipment failures; Knowledge AI team doing NLU.
|
||||
- **"Why them" angle:** Equinor already runs industrial ML at scale on safety-critical physical assets — exactly the regime Dennis shipped at Bosch (ML inference in a 24/7 wafer fab, zero downtime tolerance). The agentic layer is new for everyone (only ~11% of enterprises in production per 2026 data); Dennis brings the production-reliability + responsible-AI discipline that separates demos from deployed systems. Norwegian + prior year working in Norway = genuine relocation/culture fit.
|
||||
|
||||
## Framing Strategy
|
||||
- **Lead narrative:** "Production-AI/MLOps engineer who ships and operates ML/AI in zero-downtime industrial environments — pairing deployment reliability, security/responsible-AI ownership, and hands-on LLM-integration + agentic-tooling experience." Reach toward architect/manager via Staff-level ownership + stakeholder leadership, WITHOUT claiming agent-framework or Azure depth.
|
||||
- **Reframing map:**
|
||||
- Data Mesh / data products / metadata mgmt on AWS (SW-7) → "reference architecture for agentic systems; governed, discoverable data layer that agents query (grounded retrieval / MCP tool-data access / speak-to-data)" — LEAD agentic bridge, mirrors Equinor Omnia
|
||||
- Bosch ML inference in 24/7 fab → "production AI from concept to deployment; reliability, safe rollout in safety-critical ops" (mirrors Equinor Prevent)
|
||||
- Bosch image defect classification → "multimodal: image understanding in production"
|
||||
- Fraunhofer ARTUS → "applied NLP / speech-to-text (contributing dev)" — multimodal preferred qual
|
||||
- LiteLLM → "structured LLM integration with enterprise APIs via self-built LLM gateway (multi-provider)"
|
||||
- Custom GPTs + grounded domain knowledge → "prompt design + grounded retrieval over enterprise knowledge" (hedge — internal GPTs, not production RAG)
|
||||
- Kiro (agentic AI IDE) → "hands-on with agentic dev tooling / MCP-based tool access" (conceptual MCP)
|
||||
- Security Champion + data governance → "responsible AI: privacy-by-design, GDPR, risk monitoring, policy-as-code mindset, safe execution"
|
||||
- K8s + GitLab CI/CD + on-call SLA → "engineering quality, reliability, cost efficiency; safe fallback/rollback"
|
||||
- Kafka → "events/messaging integration"
|
||||
- Component Owner + B2B data products + Leadership Cohort + mentoring → "technical direction, stakeholder alignment, mentoring"
|
||||
- **Emphasize:** Bosch production ML (LEAD), LiteLLM LLM gateway, Security/responsible-AI, K8s/Docker/CI-CD, multimodal (image+speech), stakeholder/technical leadership.
|
||||
- **Downplay:** Pure ETL/BI framing, Teradata legacy detail, test automation, anything implying Azure or named agent frameworks.
|
||||
- **CL hooks:** Equinor Prevent (520+ production models, rotating equipment) ↔ Bosch 24/7 fab ML; agentic layer is early everywhere → bring production-reliability + responsible-AI discipline; Norway relocation + Norwegian basic + prior year in Norway; safety/zero-harm culture ↔ Security Champion + zero-downtime ops.
|
||||
- **User directives:** NEVER list LangChain/LangGraph/LlamaIndex/Semantic Kernel/AutoGen. Security Champion = 2025/26 ONLY (not 3 yrs). No Azure claims. No fabricated tools. Don't oversell C++.
|
||||
|
||||
## Critique Context
|
||||
- **Reviewer persona:** Equinor AI/architecture hiring lead or principal engineer — runs production ML at scale (Prevent/EurekaML), Azure-native, pragmatic about the demo-to-production gap. Impressed by: real production ML under operational constraints, reliability/safety rigor, honest responsible-AI substance. Bored/alarmed by: buzzword agent-framework name-dropping with no depth, inflated GenAI claims.
|
||||
- **Competitive landscape:** "Obvious fit" = someone who has shipped LLM agents with LangGraph/Semantic Kernel on Azure OpenAI + RAG in production. We do NOT have that. Our edge: rarer industrial zero-downtime production-ML credibility + security/governance discipline + Norway fit. We win on reliability/responsibility, not on agentic-framework hours.
|
||||
- **Domain vocabulary:** orchestration, grounded retrieval, MCP, guardrails, bounded autonomy, human-in-the-loop, policy-as-code, EU AI Act, reference architecture, Omnia/Prevent (Equinor-specific — use sparingly, only in CL).
|
||||
|
||||
## Cover Letter Plan
|
||||
- **Institution type:** Industry — major energy company, applied AI/architecture org
|
||||
- **Paragraph count:** 4 paragraphs, ~280 words (1 page)
|
||||
- **P1 hook:** Equinor Prevent / industrial ML at scale ↔ my Bosch 24/7 fab production-ML deployment (zero downtime). Establish production credibility + honest pivot framing.
|
||||
- **P2-P3 evidence:** LiteLLM LLM gateway + custom grounded GPTs + agentic dev tooling (LLM integration); Security Champion + data governance (responsible AI, GDPR, safe execution); K8s/CI-CD reliability. Honest about reaching toward agentic architecture, leading with production discipline.
|
||||
- **Domain pivot:** "The agentic layer is new for nearly everyone — what I bring is the production-reliability and responsible-AI discipline that turns prototypes into systems you can trust on safety-critical assets."
|
||||
- **Jargon level:** Technical but HR-safe
|
||||
- **Hook verification (DONE):** Prevent = Omnia.Prevent, 520+ ML models in production on rotating equipment; AI saved Equinor ~$130M in 2025 via predictive maintenance. Source: equinor.com/energy/machine-learning + rigzone.com (07 Jan 2026). Net-zero-2050 / 170M people / Norway locations / zero-harm culture direct from JD.
|
||||
- **"Why them" hook:** Energy transition + Norway relocation (prior year working in Norway, Norwegian basic) + safety/zero-harm culture ↔ my security-first, zero-downtime track record.
|
||||
|
||||
## Bullet Plan (CONFIRMED — 15 bullets)
|
||||
|
||||
### Position 1 — Swisscom (6 bullets) — theme: Agentic-AI Data Foundations, LLM Integration & Responsible-AI Engineering
|
||||
| # | ID | Achievement | Variant |
|
||||
|---|-----|------------|---------|
|
||||
| 1 | SW-7 | Data Mesh + data products + metadata mgmt on AWS = agentic data foundation (LEAD) | 2L |
|
||||
| 2 | SW-GenAI | Custom GPTs + LiteLLM gateway + Kiro agentic assistants (LLM-to-enterprise-API) | 2L |
|
||||
| 3 | SW-5 | Security Champion 2025/26 + data governance → responsible AI, GDPR, policy-as-code | 2L |
|
||||
| 4 | SW-1 | AWS cloud-native migration (S3, Glue, Athena/Iceberg, Redshift, Airflow, CloudFormation) | 2L |
|
||||
| 5 | SW-3 | Python services on Kubernetes + GitLab CI/CD (reliable rollout/rollback) | 2L |
|
||||
| 6 | SW-2 | Component Owner Fulfillment ETL (Oracle/Kafka→Teradata), SLA + governance | 2L |
|
||||
|
||||
### Position 2 — Bosch (4 bullets) — theme: Production ML from Concept to Deployment in 24/7 Manufacturing
|
||||
| # | ID | Achievement | Variant |
|
||||
|---|-----|------------|---------|
|
||||
| 1 | BS-1 | ML inference into 24/7 fab (Docker/K8s/Ansible), automated image defect classification (LEAD) | 2L |
|
||||
| 2 | BS-4 | ELK + Kafka anomaly detection; Grafana/Prometheus/Loki observability | 2L |
|
||||
| 3 | BS-3 | Application Owner — SLOs, vendor mgmt, training, docs | 2L |
|
||||
| 4 | BS-2 | Python/Java/C# data services over Oracle/Hadoop | 2L |
|
||||
|
||||
### Position 3 — Fraunhofer (2 bullets) — theme: Applied NLP, Speech Recognition & Microservice Engineering
|
||||
| # | ID | Achievement | Variant |
|
||||
|---|-----|------------|---------|
|
||||
| 1 | FC-2 | ARTUS — ML/NLP speech-to-text for sea-rescue transcription (hedged: contributed) | 2L |
|
||||
| 2 | FC-3 | MISSION microservices (Express.js, Docker) — data-exchange APIs | 2L |
|
||||
|
||||
### Position 4 — Vizrt (2 bullets, Bergen NORWAY) — theme: Distributed Real-Time Backend Engineering
|
||||
| # | ID | Achievement | Variant |
|
||||
|---|-----|------------|---------|
|
||||
| 1 | VZ-1 | Distributed real-time transcoding backend (Python, legacy C++) — CNN/BBC/Al Jazeera | 2L |
|
||||
| 2 | VZ-2 | A/V test suite + CI/CD quality gates | 2L |
|
||||
|
||||
### Position 5 — Generali (1 bullet) — theme: Technical Leadership, Test Automation & Java Backend
|
||||
| # | ID | Achievement | Variant |
|
||||
|---|-----|------------|---------|
|
||||
| 1 | GN-1 | Introduced BDD + trained teams / Java Community (technical leadership) | 2L |
|
||||
|
||||
**Budget:** 15 variable bullets (30 rendered lines) + ~17-18 skill lines. Reserves if page under-fills: FC-1 (Jenkins CI/CD), GN-3 (Java/J2EE).
|
||||
**Forced exclusions:** LangChain/LangGraph/LlamaIndex/Semantic Kernel/AutoGen; Azure; Solidity/Kraken crypto. Security Champion 2025/26 only.
|
||||
|
||||
## Output Files
|
||||
- Resume: `output/Equinor_AI_Manager/e2e_equinor_ai_manager_resume.tex`
|
||||
- Cover Letter: `output/Equinor_AI_Manager/e2e_equinor_ai_manager_cover_letter.tex`
|
||||
- Critique: `output/Equinor_AI_Manager/critique_equinor_ai_manager.md`
|
||||
|
||||
## Status
|
||||
- Phase 0: DONE
|
||||
- Phase 1: DONE (17 bullets confirmed — added reserves FC-1, GN-3 for page fill)
|
||||
- Phase 2 Resume: DONE — compiled 2 pages, all bullets within char limits, 0 em-dashes, no -ing endings
|
||||
- Cover Letter: DONE — compiled 1 page, 313 words, 0 em-dashes, no banned words, hooks verified (Prevent 520+ models / $130M). 4 paragraphs.
|
||||
- Critique: CURRENT — **Pass 2 = 80.0/100** (Pass 1 77.5 → +2.5). Converged near achievable ceiling (~81, metrics excluded per user; hard ceiling ~83). No remaining Tier 1 fixes.
|
||||
- **Next:** Submit — run finalization (rename PDFs for submission).
|
||||
|
||||
## Critique Summary (Pass 1, 2026-05-27)
|
||||
- **Score:** 77.5/100 → +Tier1 ≈80.5 → max ≈82 → hard ceiling ≈83.
|
||||
- **Compile:** Resume 2pp clean; CL 1pp clean. 0 em-dashes in output (17 `---` hits are LaTeX comment dividers). All bullets within char limits. Page 2 ~30% underfill (cosmetic, skip).
|
||||
- **Interview likelihood:** ATS ~80%, Recruiter ~55%, HR ~50%, HM ~30-40%, Tech panel CONCERNS-but-credible.
|
||||
- **Tier 1 fixes (do these, ~+2 pts) — REVISED per user 2026-05-27:**
|
||||
1. **SW-7 verb fix + data-layer architecture** (accuracy + on-title win). Data Mesh/ODP is a company-wide migration Dennis contributed to, NOT solo-built. Approved rewrite (216 chars): "Helped move Swisscom from legacy Teradata to a cloud **Data Mesh** on **AWS**; modelled and built governed **data products** and onboarded source systems onto the foundation AI and **agentic workflows** query for grounded retrieval." + summary hedge ("design and build governed data products on the company's AWS Data Mesh"; opener "Software and AI engineer"). **Do NOT self-title "Solution Architect"** (certs = basic architecture grounding only). ~+1.2
|
||||
2. Add "orchestration" + "reference architecture / solution patterns" where truthful (skills + ODP framing). ~+0.8
|
||||
3. ~~Quantified metric~~ — **REMOVED: user does not want quantifications.** "Measurable business impact" gap accepted; ceiling ~81 with Tier 1.
|
||||
- **Tier 2 (optional):** fix 3 participial bullet endings (B4 enabling / B8 providing / B10 supplying — AI fingerprint); trim CL ≤300 words.
|
||||
- **Findings:** One overclaim caught (SW-7 sole-build → hedged, above). Otherwise clean: Security Champion 2025/26 ✓, no LangChain/agent frameworks ✓, no Azure ✓, languages correct ✓, Generali=Hamburg ✓. CL cohesion strong, all claims traceable.
|
||||
- Critique file: `output/Equinor_AI_Manager/critique_equinor_ai_manager.md`
|
||||
|
||||
## Edit 1 Baseline (2026-05-27)
|
||||
- Pages: 2
|
||||
- Char violations: none (B6 208 / B12 211 / B16 209 = NEAR MAX but within 218)
|
||||
- Orphan violations: none
|
||||
- White space last page: ~30% of page 2 (acceptable for honest 2pp)
|
||||
- Variable bullets: 17 (34 rendered lines)
|
||||
|
||||
### Edit 1 (2026-05-27): Tier 1 + Tier 2 fixes
|
||||
- **Changes (resume):**
|
||||
1. SW-7 verb fix (accuracy): "Built a Data Mesh…" → "Helped move Swisscom off legacy Teradata to a cloud **Data Mesh** on **AWS**; modelled and built governed data products and onboarded source systems that **agentic workflows** query for grounded retrieval." (193 chars, 2L; bold reduced to 29 so it fits 2 lines — first compile rendered 3L due to bold penalty, corrected).
|
||||
2. Summary hedge: "Software engineer" → "Software and AI engineer"; "I build the AWS Data Mesh and governed data products" → "I design and build governed data products on the company's AWS Data Mesh" (555 chars).
|
||||
3. Skills: added `orchestration` (Agentic/MLOps line, dropped redundant "model deployment") + `reference architecture` (Data Foundations line, dropped "data catalog").
|
||||
4. Tier 2 — fixed 3 participial `-ing` endings: B4 (enabling→for), B8 (providing→for; re-added "log aggregation"), B10 (supplying→that gave; +"reliable,").
|
||||
- **Changes (cover letter):** trimmed 313→300 words; **fixed same sole-ownership phrasing for cohesion** ("I build the layer… an AWS Data Mesh… I own it" → "I build the data layer… governed data products on the company's AWS Data Mesh… I own them").
|
||||
- **Source:** critique Tier 1.1/1.2 + Tier 2; user accuracy correction (Data Mesh ownership) + user "do Tier 2 now / keep onboarded".
|
||||
- **Verification:** resume 2pp clean, CL 1pp clean; 0 char OVER, 0 orphans, 0 em-dashes in prose; CL 300 words; all `-ing` trailers gone; package cohesion intact.
|
||||
|
||||
| Metric | Before | After | Delta |
|
||||
|--------|--------|-------|-------|
|
||||
| Page count | 2 | 2 | 0 |
|
||||
| Char violations | 0 | 0 | 0 |
|
||||
| Orphans | 0 | 0 | 0 |
|
||||
| White space pg2 | ~30% | ~30% | 0 |
|
||||
| CL words | 313 | 300 | -13 |
|
||||
Reference in New Issue
Block a user