About the Role:
Chubb is looking for a Senior AI Engineer to lead the design, development, and deployment of advanced generative AI solutions that improve how we operate across the insurance lifecycle — from underwriting and claims to customer service and risk assessment. This role sits at the intersection of software engineering, applied AI, and technical leadership, turning the latest LLM capabilities into reliable, production-grade systems built on our Azure and Databricks platform.
As a senior member of the team, you will not only build high-quality AI solutions, but also help shape technical direction, guide architecture decisions, mentor other engineers, and influence how AI capabilities are delivered across the organization.
Key Responsibilities:
- Lead the design and build of end-to-end generative AI applications using LangGraph, including agentic workflows, RAG pipelines, and LLM-integrated services.
- Define and drive architecture for scalable, secure, reliable, and maintainable AI solutions deployed in production.
- Develop robust, well-tested backend APIs with FastAPI, containerized via Docker and deployed on Kubernetes.
- Architect and own search and retrieval solutions using Azure AI Search and MongoDB, including design of indexing strategies, hybrid search configurations, and retrieval evaluation.
- Work within our Azure cloud environment, integrating with Azure OpenAI, Azure services, and our broader data platform.
- Collaborate with product managers, data scientists, engineers, and other stakeholders to scope and deliver AI features that address real insurance business problems.
- Own the full software lifecycle, including design, code review, testing, deployment, monitoring, and production support.
- Translate complex business requirements into well-scoped technical solutions with a strong focus on reliability, maintainability, failure modes, and operational excellence.
- Mentor and support junior engineers through design reviews, code reviews, and technical guidance.
- Contribute to technical standards, best practices, and reusable patterns for AI engineering across the team.
- Evaluate and improve model quality, retrieval strategies, prompt and agent design, and production performance over time.
- Partner with business and technical leaders to shape AI roadmaps and identify high-impact opportunities for automation and decision support
