Software Engineer, Inference - Performance Optimization
OpenAI
San Francisco
Full timeUSD 295,000 - 555,000 annuallyFunction: Software EngineeringSkills: ["Performance profiling","Benchmarking","Analysis","Optimization","Distributed systems","Cost-to-serve","Microbenchmarks"]Join OpenAI's Inference team to model and optimize performance across application, model, and fleet layers. Build cost-to-serve estimates from microbenchmarks, analyze end-to-end inference workloads, and develop tooling to identify bottlenecks in latency and throughput, enabling cross-functional improvements for future launches.
