JOBS / OpenAI

Software Engineer, Inference - Multi Modal

San Francisco

Role

The role involves designing and implementing inference infrastructure for large-scale multimodal models at OpenAI. Candidates must optimize systems for high-throughput, low-latency delivery of image and audio workloads.

Location: San Francisco
Employment: unspecified
Work pattern: unspecified
Seniority: unspecified

inference systemsGPU-based ML workloadsvLLMTensorRT-LLMdistributed compute

APPLY ON THE EMPLOYER’S SITE ↗

Source and currency

This vacancy came from the organization’s official Ashby feed. Source update: 2025-05-21T18:27:41.612+00:00. Check the employer’s page for the complete description, current availability and application terms.

OpenAI RESEARCH PROFILE ↗