Lead and mentor an AI engineering team to design, architect, and deploy production-ready multi-agent, LLM-powered systems. Define technical strategy, set architecture and security standards, implement hybrid control flows/state machines, integrate agent-to-tool and agent-to-agent protocols, and collaborate with product and business teams to translate requirements into scalable microservices.

Designs, develops, and deploys enterprise-grade autonomous AI services and multi-agent workflows. Integrates MCP and A2A protocols, architectures hybrid control flows, secures tool execution, and builds scalable microservices. Applies SRE practices such as fallbacks, circuit breakers, audit trails, and observability. Requires advanced Python, cloud foundation model platforms, containerization, CI/CD, distributed systems, and production LLM deployment experience.

Lead and grow a team of Agentic AI engineers to transition multi-agent and generative AI POCs into scalable, secure, production-ready services. Define technical roadmap, guide architecture for scalability and cost, champion agent interoperability standards, and establish CI/CD, observability, and delivery practices for LLM-powered applications that drive business impact.