Global AI MapJOBS / OpenAI
Software Engineer, Model Runtime
San Francisco
Role
The role involves building the model runtime for the inference engine on OpenAI's custom silicon. Candidates must design and implement LLM inference runtimes, focusing on scheduling, memory management, and distributed execution.
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: 2026-08-24T16:34:31.338+00:00. Check the employer’s page for the complete description, current availability and application terms.