13h ago
Software Engineer, Productivity - Inference Runtime
San Francisco, CA
$230k-$385k / year
full-timeseniorai-ml
๐ Tech Stack
๐ผ About This Role
You'll build tooling and infrastructure for deploy gate validation and release engineering on OpenAI's inference runtime teams. Your work ensures model launches are safe, performant, and regression-free. This is high-impact infrastructure for one of the largest inference platforms in the world.
๐ฏ What You'll Do
- Improve deploy gate validation tooling and infrastructure
- Harden CI and testing infrastructure for reliability
- Build automation for failure triage and escalation
- Reduce developer friction in testing and release workflows
๐ Requirements
- Experience with CI/CD systems and release tooling
- Python proficiency for deployment infrastructure
- Ability to debug complex distributed systems
- Strong developer empathy and ownership mindset
โจ Nice to Have
- C++ experience near inference engine code
- Prior inference system knowledge
๐ Benefits & Perks
- ๐ฐ Competitive salary range $230K-$385K
- ๐๏ธ Flexible PTO
- ๐ฅ Health insurance (medical, dental, vision)
- ๐ Equity package
- ๐ค Access to latest AI tools
๐จ Hiring Process
Estimated timeline: 2-4 weeks ยท AI estimate
- 1Recruiter Screenยท 30 min
- 2Technical Phone Interviewยท 60 min
- 3Onsite Final Roundsยท Half day
0 0 0