Software Engineer, Productivity - Inference Runtime

Highlights

• Harden deploy gates ensuring inference engine images are correct and performant.
• Build automation for failure triage, ownership detection, and safe rollouts.
• Support model launches across ChatGPT, Codex, API and research workloads.

Ideal candidate

High-ownership engineer with strong developer empathy who loves making other engineers faster and safer. Comfortable with ambiguity and motivated by improving reliability of large-scale production systems.

Requirements

• Strong experience with CI/CD systems, testing infrastructure, release tooling, or large-scale validation systems
• Comfortable working in Python-heavy environments and debugging complex distributed systems
• High ownership and ability to operate in ambiguous areas without a fully predefined roadmap
• Strong developer empathy with focus on reducing friction and making engineers more effective
• Experience building automation for failure triage, ownership detection, and escalation
• Pragmatic, collaborative mindset motivated by helping teams move faster with confidence