OpenAI
San Francisco, California
Software Engineer, Inference - Performance Optimization
Job details
- Location
- San Francisco, California
- Work type
- Onsite
- Posted
- Apr 25, 2026
- Apply on
- jobs.ashbyhq.com
About this role
Build and refine performance models, analyze workloads end-to-end, enhance tooling, and collaborate with teams.
What you'll do at OpenAI:
- Build performance models
- Analyze workloads
- Enhance tooling
Apply to this Software Engineer, Inference - Performance Optimization role at OpenAI with a tailored resume on ApplyBolt.