Build and maintain agent skills, tooling, and evaluation infrastructure: CLIs, libraries, CI workflows, metrics, safety gates, and observability for agent behavior. Design evaluation datasets, investigate failures, and collaborate with product and security teams to ship reliable, reusable internal systems.

Serve as the primary technical owner for customer engagements, design and build integrations, write production-quality code, troubleshoot and ship scalable production solutions, capture precise product feedback, and partner with product and engineering to convert field learnings into roadmap improvements.