jobs
Software Engineer, Inference - Performance Optimization
About the Team Our team analyzes inference stack performance across the application, model, and fleet layers to identify bottlenecks and drive faster, cheaper inference.
En anglais
- Company
- OpenAI
- Location
- San Francisco
- Status
- Closed
- Posted
- 2026-04-25 02:24 UTC
OpenAI is hiring a software engineer for inference performance optimization, on-site in San Francisco. The work spans the inference stack at application, model and fleet layers: profiling, benchmarking and modeling to find latency and throughput bottlenecks, turning microbenchmark results into cost-to-serve estimates, and building tools that let other teams weigh latency, capacity, utilization and cost. The posting asks for first-principles reasoning about distributed systems, model inference and hardware efficiency, and comfort ranging from application behavior to kernels, accelerators, networking and fleet scheduling.
Original job posting