OpenAI
Software Engineer, Developer Productivity - Inference Runtime
$230K–$385K
San Francisco +1 · Hybrid · Full-time · Posted May 10, 2026
- Location
- San Francisco
Seattle
About the job
Build and improve developer productivity, CI, validation, and release systems that help inference teams safely deploy reliable, performant model-serving infrastructure.
What you'll do
- Improve deploy gates and validation for inference engine releases, including correctness, performance, and regression checks.
- Harden CI, testing, canary, and rollout workflows; reduce flaky failures and improve observability and release safety.
- Automate failure triage, ownership detection, debugging, and escalation while reducing friction in developer workflows.
What they ask for
- Strong experience with CI/CD systems, testing infrastructure, release tooling, developer productivity, or large-scale build and validation systems.
- Comfort working in Python-heavy environments and debugging complex distributed systems.
- High ownership and ability to work through ambiguous, cross-functional operational problems.
Nice to have
- C++ experience is helpful but not required.
- Prior inference experience is not required.
Pay
$230K – $385K USD base salary
Tools
Python, C++
AI focus
Supports inference systems that serve models, including release validation and safe deployment of inference optimizations.
Model-written summary · the original posting is authoritative