Software Engineer, Inference - Performance Optimization

OpenAI · San Francisco

OpenAI is hiring a Software Engineer, Inference - Performance Optimization in San Francisco. The role focuses on databases & storage, networking, graphics, gpu & compute, low-latency & performance.

Key responsibilities

• You will build cost-to-serve estimates from microbenchmarks and create tools that help cross-functional teams reason about latency, capacity, utilization, and cost tradeoffs.
• Build and refine performance models that translate microbenchmark results into cost-to-serve estimates.
• Enjoy reasoning from first principles about distributed systems, model inference, and hardware efficiency.

Source and corrections

NearMetal classified and summarized this role from an official company source.