Software Engineer, Productivity - Model

Software Engineer, Productivity - Model Performance

Runtime - San Francisco

We’re hiring software engineers to make OpenAI’s Model Performance teams more productive. These teams work on the systems, tooling, and infrastructure that help improve model performance across OpenAI’s training and inference workloads at frontier scale.

We’re looking for an autonomous, high-ownership developer productivity engineer who cares deeply about helping other engineers move faster, safer, and with more confidence.

This role will sit within OpenAI’s Model Performance organization, contributing to developer infrastructure, CI systems, testing workflows, tooling, and broader performance infrastructure efforts. There is also a strong opportunity to contribute to the Triton project and help improve the systems that support performance‑critical engineering work across OpenAI.

• Improve development workflows for engineers working on model performance infrastructure
• Design and improve CI/CD, release, validation, and testing pipelines
• Build and maintain tools that improve reliability, iteration speed, and engineering confidence
• Partner closely with engineers to identify friction in testing, debugging, deployment, and development workflows
• Contribute to infrastructure efforts that support performance‑critical training and inference systems
• Help improve developer experience across Python‑heavy codebases and performance‑oriented infrastructure
• Work in a high‑context, ambiguous environment where ownership and good judgment matter

• You are motivated by enabling the people around you and helping engineers do their best work
• You have strong experience with CI/CD, developer infrastructure, testing systems, tooling, or build/release workflows
• You are highly collaborative, empathetic, and comfortable partnering deeply with technical teams
• You are strong in Python and enjoy building reliable, scalable developer tools and infrastructure
• You have experience improving large‑scale engineering workflows, especially around CI reliability, test infrastructure, and debugging velocity
• You are self‑directed and comfortable operating with ambiguity
• You do not need direct inference or model performance experience, but you are excited to learn the domain and make the team meaningfully more effective
• Experience in the PyTorch ecosystem is highly relevant
• Experience with C++ or Rust is a nice‑to‑have, but not required
• When you see repeated friction—slow tests, flaky CI, brittle release processes, painful debugging, unclear validation—you instinctively fix the underlying system
• You are pragmatic and know how to balance high standards with forward progress

$230K – $385K

We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic.