Build and operate the AI platform and runtime infrastructure for LLM/agent-powered products. Deliver CI/CD pipelines, model serving (self-hosted and managed), eval frameworks, key management, observability, cost controls, and developer tooling. Partner with AI, software, security, and finance teams and produce runbooks, docs, and best practices to ensure reliable, secure, and cost-effective AI deployments.

Architect and build AI-native production systems across a multi-language stack, design offline and online evaluation frameworks for LLMs, monitor live model behavior and drift, lead architecture reviews, mentor senior engineers, and prototype and ship AI capabilities while ensuring reliability and correctness in a regulated domain.