Global AI MapJOBS / OpenAI
Software Engineer, Inference - Performance Optimization
San Francisco
Role
The role involves modeling inference performance across application, model, and fleet layers to build cost-to-serve estimates. Candidates must analyze workloads end-to-end and enhance tooling to identify bottlenecks for latency and throughput.
Location: San Francisco
Employment: unspecified
Work pattern: unspecified
Seniority: unspecified
APPLY ON THE EMPLOYER’S SITE ↗
Source and currency
This vacancy came from the organization’s official Ashby feed. Source update: 2026-04-25T02:24:38.573+00:00. Check the employer’s page for the complete description, current availability and application terms.