Lead end-to-end LLM inference performance across serving systems, models, GPU hardware, and workloads. Define rigorous benchmarks, diagnose bottlenecks from scheduling through kernels and interconnects, optimize single- and multi-node deployments, and deliver production-ready runtimes and configurations. Collaborate with product and infrastructure teams, evaluate inference technologies, and implement runtime fixes. The role requires strong Python engineering, production experience with serving engines such as vLLM or SGLang, GPU profiling, and knowledge of modern inference optimization techniques.

Lead strategy, roadmap, and business performance for a core AI infrastructure product area. Drive customer research, KPI-driven roadmaps, business cases, cross-functional launches, and measurable outcomes for adoption, retention, revenue, and platform expansion.

Build and maintain frontend and backend components for an AI infrastructure platform using Python and TypeScript. Contribute to SDK development, collaborate with engineering and AI teams, write tests and maintain code quality, participate in code reviews, and support developer-focused tooling and integrations.