JOBS / OpenAI

Software Engineer, Workload Enablement

San Francisco; Seattle

Role

This role involves enabling production workloads and end-to-end testing on new platforms by creating test harnesses and stress benchmarks. The position requires porting inference and training workloads to new hardware and analyzing performance bottlenecks across compute, networking, and storage systems.

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

PyTorchDistributed SystemsRDMANCCLPerformance Engineering

APPLY ON THE EMPLOYER’S SITE ↗

Source and currency

This vacancy came from the organization’s official Ashby feed. Source update: 2026-03-28T00:39:41.241+00:00. Check the employer’s page for the complete description, current availability and application terms.

OpenAI RESEARCH PROFILE ↗