Leads technical delivery for AI workstreams across regulated client engagements, balancing hands-on engineering with oversight of three to five engineers. Designs and reviews LLM systems, retrieval and agent architectures, extraction pipelines, evaluation gates, security controls, and offline deployments. Mentors engineers, manages design and code reviews, communicates delivery risk to leadership and clients, and builds reusable Center of Excellence assets. Requires production LLM experience, deep Python and system design expertise, cloud depth, evaluation rigor, and technical leadership.