Design, build, and ship production-grade AI agents that interact with real users and systems at scale. Build evaluation, testing, and monitoring systems to ensure agent reliability, safety, and continual improvement. Architect flexible, modular workflows that make it easy to extend and iterate on AI capabilities. Integrate agents with existing backend APIs and data systems, collaborating with backend engineers to expose the right capabilities. Translate early AI prototypes into scalable, maintainable production systems used by millions of people. Take ownership of Insight Timer’s GenAI infrastructure — shaping best practices, frameworks, and internal tooling. Design data and feedback pipelines that help improve agent performance through real-world usage and, when appropriate, fine-tuning. Stay current with emerging agent frameworks and infrastructure approaches (e.g. LangGraph, CrewAI, AutoGen), adopting new techniques when they support product goals.