Engineering Manager, Inference Benchmarking — AI Perf
NVIDIA
Santa Clara, Austin
Workplace: HybridFull timeUSD 224,000 - 356,500 annuallyFunction: Data Science & Machine LearningExperience: 8+ yearsEducation: bachelorsSkills: ["Leadership","Communication","Mentoring","Cross-functional collaboration","Strategic thinking"]Lead the engineering team building and advancing NVIDIA AIPerf, a benchmarking platform for LLM inference across datacenter, edge, and local deployments. Drive the core infrastructure roadmap (load generation, GPU telemetry, microservices), ensure accurate benchmark results, and mentor senior engineers in an open-source, high-velocity environment while collaborating with Dynamo, NIM, and external contributors.
