GenAI Lead / GCP AI Engineer Lead

Capgemini • New York, NY

3d • $105,000 - $115,000

About The Position

Build, test, and deploy production generative AI solutions on Google Cloud for insurance clients, including document summarization, intelligent intake, underwriting and claims assistants, and agentic workflows. The role turns architecture into working code and owns features from prototype through production. Work includes developing applications with Gemini models and Google Cloud AI services, creating retrieval-augmented generation pipelines and agents, integrating APIs and data services, deploying services, evaluating quality and operational performance, applying security guardrails, and collaborating with QA, UI, and data teams in Agile sprints. The position is located in Hartford, Connecticut. The posted base compensation range is $105,000–$115,000. Additional variable incentives, bonuses, or commissions may be available depending on the position and applicable laws.

Requirements

• Strong Python skills, including FastAPI or Flask, asynchronous programming, and pytest.
• Hands-on experience with the Gemini API, Vertex AI SDK, or Google Gen AI SDK.
• RAG design experience and familiarity with at least one vector store: Vector Search, AlloyDB pgvector, or BigQuery vector search.
• Experience with an LLM framework such as ADK, LangChain, or LangGraph.
• Knowledge of core GCP services: Cloud Run, Cloud Functions, Cloud Storage, BigQuery, IAM, and Secret Manager.
• REST API design, Git, Docker, and CI/CD skills.
• Good written and verbal communication skills for working with onsite and client teams.

Nice To Haves

• Insurance domain experience, including P&C, E&S, specialty, or workers' compensation, or financial services experience.
• Experience with Document AI custom extractors and OCR for scanned or handwritten forms.
• Experience with Agent2Agent (A2A) protocol or Model Context Protocol (MCP) tool integration.
• Model tuning experience, including supervised fine-tuning on Gemini, and model monitoring.
• Terraform experience.
• Looker or Looker Studio dashboard experience.
• Google Cloud Professional Machine Learning Engineer certification.
• Google Cloud Associate Cloud Engineer or Professional Cloud Developer certification.
• Google Cloud Generative AI Leader certification.

Responsibilities

• Build generative AI applications with Gemini models on the Gemini Enterprise Agent Platform (Vertex AI).
• Design and tune prompts, structured outputs, and function calling for insurance documents, including submissions, ACORD forms, certificates of insurance, loss runs, and policies.
• Build RAG pipelines using chunking, embeddings, Vector Search or Vertex AI Search, grounding, and citations.
• Build agents with the Agent Development Kit (ADK), deploy them on Agent Engine, and integrate tools and APIs.
• Extract and classify documents using Document AI and Gemini multimodal input.
• Deploy services on Cloud Run or GKE, expose them through Apigee, and implement CI/CD with Cloud Build.
• Move and store data using BigQuery, Cloud Storage, Pub/Sub, and Dataflow.
• Create evaluation sets and assess quality, latency, and cost using the Gen AI evaluation service and golden datasets.
• Apply guardrails, including PII masking with Sensitive Data Protection (DLP), safety filters, and least-privilege IAM.
• Collaborate with QA, UI, and data teams in Agile sprints; write clean, tested, and documented code.
• Own features from prototype through production.

Benefits

• Paid time off based on employee grade, including 12–25 vacation days depending on grade, company-paid holidays, personal days, and sick leave.
• Medical, dental, and vision coverage (or provincial healthcare coordination in Canada).
• Retirement savings plans, such as 401(k) in the U.S. or RRSP in Canada.
• Life and disability insurance.
• Employee assistance programs.
• Other benefits as provided by local policy and eligibility.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed