9 days ago
Base Salary
$105k - $115k/yr
Responsibilities
- Build, test, and deploy production GenAI applications with Gemini models on Google Cloud for insurance clients.
- Design prompts, structured outputs, function calling, RAG pipelines, chunking, embeddings, grounding, and citations for insurance documents.
- Build agents with the Agent Development Kit, deploy them on Agent Engine, and integrate tools and APIs.
- Extract and classify documents using Document AI and Gemini multimodal input, including scanned and handwritten forms.
- Ship services on Cloud Run or GKE, expose them through Apigee, and manage CI/CD with Cloud Build.
- Move and store data using BigQuery, Cloud Storage, Pub/Sub, and Dataflow.
- Create evaluation sets and perform quality, latency, cost, and model monitoring checks using golden datasets and GenAI evaluation services.
- Apply guardrails, PII masking, safety filters, and least-privilege IAM while writing clean, tested, and documented code with QA, UI, data, and client teams.
Requirements
- 4–8 years of experience in software, data, or ML engineering, including 1–5 years of hands-on GenAI experience with Vertex AI and Google Cloud Platform.
- Strong Python skills and experience with FastAPI or Flask, asynchronous programming, and pytest.
- Hands-on experience with the Gemini API, Vertex AI SDK, or Google Gen AI SDK.
- Experience designing RAG systems and using at least one vector store, such as Vector Search, AlloyDB, pgvector, or BigQuery vector search.
- Experience with LLM frameworks including ADK, LangChain, or LangGraph.
- Experience with GCP services including Cloud Run, Cloud Functions, Cloud Storage, BigQuery, IAM, and Secret Manager.
- Experience designing REST APIs and using Git, Docker, and CI/CD.
- Strong written and verbal communication skills for working with onsite and client teams.
- Preferred insurance, financial services, PC/ES, specialty, or workers’ compensation experience.
- Preferred experience with Document AI custom extractors, OCR, A2A, MCP, supervised fine-tuning, model monitoring, Terraform, Looker, or Looker Studio.
- Preferred Google Cloud Professional Machine Learning Engineer, Google Cloud Associate Cloud Engineer, Google Cloud Professional Cloud Developer, or Google Cloud Generative AI Leader certification.
Benefits
- Hartford, Connecticut location with three days per week in the office.
- Comprehensive benefits package for regular full-time employees, including 12–25 vacation days based on grade, company 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 and employee assistance programs.
Tech Stack
Categories
AI ApplicationsData Engineering
About Capgemini
Capgemini is a global IT services and consulting firm that delivers strategy, cloud, AI, software engineering, and managed services to large enterprises and public-sector clients. Founded in 1967 and headquartered in Paris, it is publicly traded on Euronext Paris and operates in 50+ countries. The group expanded its engineering capabilities by acquiring Altran in 2020, now operating as Capgemini Engineering.