8.3 KiB
8.3 KiB
Session: Google — Senior Forward Deployed Engineer, GenAI, Google Cloud
JD Info
- File: JDs/temp_google_fde_genai.txt
- Role: Senior Forward Deployed Engineer, GenAI, Google Cloud
- Company: Google (Google Cloud — Go-To-Market / Worldwide Field Operations)
- Bundle: ML/AI Engineer (primary) + Data Engineer (secondary, for the pipeline/RAG-data angle)
- Format: Resume (2-page, resume.cls) + 1-page cover letter
- Locations: Zürich (also Vienna, Berlin, Hamburg, Munich) — German-speaking region, NO French requirement
- Comp context: FDE GenAI bands anchor near top of market (~$238k avg US, into high $400k senior). Clears the 180k+ CHF bar easily.
JD Analysis
Requirements
| # | Requirement | Match | Evidence |
|---|---|---|---|
| 1 | Bachelor's CS/Eng or equivalent | Direct | M.Eng. Computer Aided Engineering (Software Design & Eng focus) |
| 2 | 6 yrs shipping production AI-driven solutions (Python/TS) | Bridge (MED) | Production ML inference at Bosch (24/7 fab); 6+ yr Python career; but "AI-driven solutions" for full 6 yrs is a stretch — GenAI specifically is recent |
| 3 | Lead technical discovery w/ business stakeholders | Bridge (MED-HIGH) | Swisscom B2B data products, Product Owner collaboration, Component Owner, stakeholder analytics |
| 4 | Design/build AI systems on GCP | Gap/Bridge (LOW) | AWS-certified & AWS-native (S3/Glue/Athena/Redshift); GCP not used. Bridge: "cloud-native AI infra, transferable to GCP" |
| 5 | Pipelines for structured/unstructured data + vector DBs + RAG | Split | Pipelines: Bridge-HIGH (ETL, Kafka, AWS, PySpark). Vector DBs + RAG: GAP — not documented |
| 6 | MSc/PhD (preferred) | Direct | M.Eng. |
| 7 | Multi-agent frameworks (LangGraph/CrewAI/ADK), ReAct (preferred) | GAP | Verified toolchain is Kiro/Copilot/LiteLLM/custom GPTs — NOT these. DO NOT fabricate. |
| 8 | LLM-native metrics: tokens/sec, cost-per-request (preferred) | Bridge (LOW-MED) | LiteLLM gateway work touches API usage/cost — but not documented as a quantified achievement |
ATS Keywords
- GenAI/AI: GenAI, LLM, agentic, RAG, vector database, multi-agent, production AI, inference
- Cloud: GCP, Vertex AI, Gemini, cloud-native (his: AWS — bridge)
- Data: pipelines, structured/unstructured data, ETL, Kafka, data readiness
- Eng: Python, TypeScript, APIs, production-grade, MLOps, Kubernetes, CI/CD
- Soft: technical discovery, stakeholder, customer-facing, white-glove deployment, ROI
Gap Assessment
- Direct: Education (M.Eng.); Python; production deployment lifecycle; stakeholder/customer-facing data delivery; data pipelines (structured); Kubernetes/CI/CD; AWS cloud-native infra
- Bridge: "production AI-driven solutions" (via Bosch ML inference + MLOps); GCP (via AWS, transferable); unstructured-data pipelines; LLM cost/usage (via LiteLLM gateway — verified tooling)
- GAP (cannot claim): RAG architectures, vector databases, multi-agent frameworks (LangGraph/CrewAI/ADK), agentic workflow production systems, Vertex AI/Gemini hands-on. The JD's GenAI core is largely undocumented in the KB.
Company Context
- Mission: Google Cloud's Go-To-Market team leading enterprise AI adoption with Gemini + Gemini Enterprise Agent Platform (formerly Vertex AI), ADK, RAG Engine, Model Garden.
- This role: Embedded builder-consultant living inside customer offices, shipping production AI code. Google is hiring hundreds of FDEs in 2026. Concentrated in finance/healthcare/retail/public-sector verticals where AI is bottlenecked by compliance, data residency, and legacy-system integration — not model capability.
- Culture: Hands-on builder (code+debug, not just architecture); white-glove customer delivery; feedback loop into product roadmap; collaborative, direct access to DeepMind eng.
- "Why them" angle: The bottleneck Google names — compliance, data residency, legacy integration — is exactly the regulated-enterprise environment Dennis works in daily at Swisscom (Switzerland's largest telco): data governance, on-call SLA, security ownership, legacy-to-cloud migration. That operational/compliance maturity is the genuine edge, not GenAI-framework depth.
Framing Strategy
- Lead narrative: "Engineer who ships production AI into demanding, regulated, real-world environments — and owns the data infrastructure and integration work that makes it actually run." Bosch (production ML inference in a 24/7 fab) + Swisscom (regulated-telco data infra, cloud migration, compliance ownership) = the FDE archetype: deploys into hard environments, solves integration/data-readiness/compliance blockers.
- Reframing map:
- Bosch ML inference containerization → "shipped production AI into a 24/7 environment with zero downtime tolerance" (the white-glove/production-blocker story)
- AWS data lake / ETL → "data-readiness and pipeline foundation that enterprise AI depends on; cloud-native, transferable to GCP"
- Component Owner + on-call + Data Governance → "solved the compliance, data-residency, and reliability blockers that stall enterprise AI" (maps to Google's stated FDE bottleneck)
- B2B data products + Product Owner collaboration → "technical discovery with business stakeholders"
- LiteLLM gateway + custom GPTs (VERIFIED tooling) → modest, honest GenAI signal: "built internal LLM-gateway/API tooling and domain-specific GPT assistants" — NO inflation into RAG/agentic production
- Emphasize: production deployment in hard environments; data-readiness/integration/compliance; stakeholder-facing delivery; Python; cloud-native infra; verified GenAI tooling
- Downplay: pure BI/analytics; testing/RPA; do not lead with "data engineer" label
- Do NOT claim: RAG, vector DBs, LangGraph/CrewAI/ADK, multi-agent production systems, Vertex AI/Gemini hands-on
- CL hooks: Google's "hundreds of FDEs in 2026" embedded model; the compliance/data-residency/legacy-integration bottleneck (Swisscom parallel); Bosch production-ML story as the opener
- User directives: No French/Italian on resume. No "Security Champion = 3 years" (it's a 2025/26 team role, not award; include only if useful — JD doesn't require security). Don't oversell C++.
Critique Context
- Reviewer persona: Google Cloud FDE hiring manager / staff FDE — wants someone who can code and ship agentic GenAI in a customer's messy environment, not a slide-deck architect. Impressed by: production-grade delivery under constraints, real integration war-stories, ROI. Bored by: generic "passionate about AI," BI dashboards, untethered tool lists.
- Competitive landscape: Competing against ex-consulting solutions engineers, AWS/GCP applied-AI specialists, and ML engineers with real RAG/agentic production reps. The "obvious fit" has shipped a RAG/agentic system on a hyperscaler. Dennis's edge must be: production-ML-in-hard-environments + regulated-enterprise data/compliance maturity.
- Domain vocabulary: Vertex AI / Gemini Enterprise, ADK, RAG Engine, agentic workflows, MCP servers, tokens/sec, cost-per-request, data residency, VPC Service Controls — insider terms Dennis can reference but must not claim hands-on beyond what's true.
Cover Letter Plan
- Institution type: Industry (Big Tech, applied AI field team)
- Paragraph count: 3-4 paragraphs, ~250-300 words
- P1 hook: Bosch production-ML story (shipped ML inference into a 24/7 fab, zero downtime) → "that's what 'production-grade reality' means to me" → tie to FDE embedded-builder mission
- P2-P3 evidence: Swisscom regulated-enterprise data infra + cloud migration + compliance/SLA ownership → map directly to Google's stated FDE bottleneck (compliance, data residency, legacy integration). Mention verified GenAI tooling (LiteLLM gateway, custom GPTs) honestly as current applied-LLM work.
- Domain pivot: "My GenAI work to date is internal tooling (LLM gateway, domain GPT assistants); what I bring to an FDE role is the harder-to-teach half — shipping AI into constrained, regulated, legacy-bound environments."
- Jargon level: Technical (engineer-to-engineer), HR-safe on specifics
- "Why them" hook: Google's 2026 embedded-FDE bet + the compliance/integration bottleneck that mirrors his daily work
Status
- Phase 0: DONE
- Phase 1: PENDING
- Next: (awaiting Phase 0 confirmation — see strategic flag on GenAI evidence gap)