Software Engineer, Productivity - Inference Runtime

About this role

Join OpenAI's Inference Runtime team as a Developer Productivity Engineer focused on building and hardening CI/CD systems, deploy gates, and validation infrastructure for model serving. You'll improve release quality, reduce flaky tests, and empower engineers to deploy safely and confidently across one of the world's largest inference platforms.

What you'll do

• Design and improve deploy gate validation systems to ensure inference engine releases are correct, performant, and regression-free
• Harden CI/CD infrastructure and reduce noisy or flaky test failures caused by environment instability
• Build automation for failure triage, ownership detection, debugging, and escalation workflows
• Improve canary, async, and large-scale validation processes for inference systems
• Partner with inference teams to streamline release, testing, and deployment workflows
• Reduce developer friction and increase engineering velocity through better tooling and self-service capabilities

What they're looking for

• CI/CD systems and infrastructure
• Release engineering and deployment tooling
• Python programming
• Testing infrastructure and test automation
• Debugging distributed systems
• C++ (helpful but not required)
• Developer empathy and workflow optimization
• Automation and operational effectiveness