Lead development of production agentic AI systems: reasoning, planning, tool orchestration, memory and grounding, evaluation frameworks, and multimodal agent coordination across chat, voice, and UI. Translate research into reliable, testable systems and iterate with founders and customers.

Build and own core backend infrastructure for long-running agentic AI workflows, ensuring high reliability, observability, disaster recovery, secure execution sandboxes, HIPAA-compliant data handling, and production-grade IAM and secrets management.