Design, deploy, automate, monitor, and secure highly available cloud infrastructure, backend services, APIs, and event-driven systems. Own observability, scalability, networking, reliability, and incident response while supporting AI, clinical, and regulated healthcare workflows. Build resilient AWS architectures, diagnose performance issues, and collaborate with science and product teams to productionize advanced systems.

Develop production-grade agentic AI systems for clinical and economic decision-making. Responsibilities include building multi-step agents, integrating LLMs with knowledge graphs and structured data, designing reliability and explainability guardrails, maintaining RAG pipelines, optimizing cost and latency, and implementing monitoring and observability. The role also involves evaluating agent behavior, handling edge cases, integrating systems into workflows, and maintaining data governance and SOC 2 standards.