Inference Performance Engineer: Latency & Cost Optimization

OpenAI; San Francisco (CA); On-site; USD 295,000 - 555,000; Full time

Job summary

OpenAI is looking for a performance modeler in San Francisco who will analyze inference stack performance and build cost-to-serve estimates. In this role, candidates should have expertise in performance profiling and enjoy reasoning about distributed systems.

The position offers a compensation range of $295K to $555K and requires collaboration with engineering and research teams to enhance performance and address system bottlenecks.

Qualifications

• Expertise in performance profiling, analysis, and optimization.
• Understanding of distributed systems and microbenchmarking.
• Ability to collaborate with engineering and research teams.

Responsibilities

• Build and refine performance models from microbenchmark results.
• Analyze inference workloads end to end across the application.
• Enhance tooling to identify bottlenecks for latency and throughput.

Skills

Performance profiling

Benchmarking

Systems analysis

Model inference

Optimization techniques

Job description

OpenAI is looking for a performance modeler in San Francisco who will analyze inference stack performance and build cost-to-serve estimates. In this role, candidates should have expertise in performance profiling and enjoy reasoning about distributed systems.

The position offers a compensation range of $295K to $555K and requires collaboration with engineering and research teams to enhance performance and address system bottlenecks.