Design, build, deploy, and operate production AI agents and multi-agent systems for insurance workflows. Responsibilities include agent orchestration, APIs, RAG pipelines, evaluation frameworks, regression testing, observability, production troubleshooting, and reliability improvements. The role requires hands-on Python software engineering, LLM application development, cloud infrastructure, and collaboration in end-to-end product pods.

Leads an AI engineering team of 4–8 engineers while remaining hands-on with architecture, coding, code reviews, and debugging. Owns delivery of production AI systems, including LLM applications, agentic workflows, document extraction, ETL pipelines, observability, monitoring, and model evaluation. Partners with product, platform, data engineering, recruiting, and customers to establish technical direction, hire talent, and deliver reliable, scalable AI features.