AI Engineer (Vertex AI)

Capgemini • New York, NY

2d • $105,000 - $115,000 • Hybrid

About The Position

The AI Engineer builds, tests, and deploys production generative AI solutions on Google Cloud for insurance clients. Solutions include document summarization, intelligent intake, underwriting and claims assistants, and agentic workflows. The role translates architecture into working code and owns features from prototype through production. It is based in Hartford, Connecticut, with work from the office three days per week.

Requirements

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

Nice To Haves

• Insurance domain experience (P&C, E&S, specialty, or workers' compensation) or financial services experience.
• Document AI custom extractors or OCR experience with scanned or handwritten forms.
• Experience with the Agent2Agent (A2A) protocol or Model Context Protocol (MCP) tool integration.
• Model tuning, including supervised fine-tuning on Gemini, and model monitoring experience.
• Terraform experience; Looker or Looker Studio dashboards.
• 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, COIs, 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 use CI/CD in Cloud Build.
• Move and store data using BigQuery, Cloud Storage, Pub/Sub, and Dataflow.
• Create evaluation sets and run quality, latency, and cost checks using the Gen AI evaluation service and golden datasets.
• Apply guardrails, including PII masking with Sensitive Data Protection (DLP), safety filters, and IAM least privilege.
• Work in Agile sprints with QA, UI, and data teams; write clean, tested, and documented code.

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 a 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.
• The role may be eligible for variable incentives, bonuses, or commissions, depending on the position and applicable laws.

What This Job Offers

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