Designs, develops, and deploys enterprise-grade autonomous AI services and multi-agent workflows. Responsibilities include integrating MCP and A2A protocols, architecting hybrid control flows, implementing secure sandboxed tool execution, building scalable microservices, and applying SRE practices for reliability, observability, fallback handling, and auditability. The role requires production experience shipping LLM-powered systems and collaboration with cross-functional teams to translate business needs into technical agent solutions.

Lead and grow an Agentic AI engineering team to move multi-agent and generative AI POCs into scalable, secure, production systems. Define technical roadmaps, ensure architecture and CI/CD/observability best practices, champion agent interoperability standards, and deliver autonomous LLM-powered services that meet business objectives.