Principal Software Engineer, Copilot Code Review

GitHub, Inc.•UNAVAILABLE, UNAVAILABLE

4d•Remote

About The Position

AI writes code faster than teams can review it, and review is now the bottleneck. Getting an agent to review as well as, or better than, a great engineer who knows your codebase is one of the most important unsolved problems in AI-assisted development. Copilot code review is GitHub's answer, and more developers get reviews from it than from any other AI reviewer, increasingly on code that agents wrote. Getting review right is hard to define and harder to measure, and no single number settles whether reviews got better. We think the AI products that win are the ones with the best evals, and we're building the best, offline and online. We run at GitHub scale with an on-call rotation, and we're a fast-growing team competing to build the best AI code reviewer in the world. As a Principal Software Engineer here, you'll be a technical owner of how Copilot code review works, and you'll be working out what this job becomes: we build the tool that's changing how engineers work, and this role leads how our own team adapts. This is a hands-on role: you'll be in the code, solving the hardest technical problems yourself, not just guiding the work.

Requirements

11+ years' experience in Software Engineering, Computer Science, or related technical discipline with proven experience maintaining and delivering production software coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, Go, Ruby, Rust, or Python.
OR Associate’s Degree in Computer Science, Electrical Engineering, Electronics Engineering, Math, Physics, Computer Engineering, Computer Science, or related field AND 10+ years' experience in Software Engineering, Computer Science, or related technical discipline with proven experience maintaining and delivering production software coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, Go, Ruby, Rust, or Python.
OR Bachelor's Degree in Computer Science or related field AND 9+ years' experience in Software Engineering, Computer Science, or related technical discipline with proven experience maintaining and delivering production software coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, Go, Ruby, Rust, or Python.
OR Master's Degree in Computer Science, Electrical Engineering, Electronics Engineering, Math, Physics, Computer Engineering, Computer Science, or related field AND 7+ years' experience in Software Engineering, Computer Science, or related technical discipline with proven experience maintaining and delivering production software coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, Go, Ruby, Rust, or Python.
OR Doctorate in Computer Science, Electrical Engineering, Electronics Engineering, Math, Physics, Computer Engineering, Computer Science, or related field AND 5+ years' experience in Software Engineering, Computer Science, or related technical discipline with proven experience maintaining and delivering production software coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, Go, Ruby, Rust, or Python.
OR equivalent experience.

Nice To Haves

Experience owning the architecture and the hardest technical calls on a large-scale production system.
Hands-on experience applying frontier models at scale, with a grounded sense of what they can and can't do.
Experience owning the evaluation that decides whether a model-driven product is improving and sharpening the evals themselves when they fall short.
Depth in Go, Ruby, TypeScript, or Python, with the operational experience of running a distributed service on call at GitHub scale.
Experience building an LLM-backed or agentic product in production or partnering with research teams to ship model capability.

Responsibilities

Drive how the review agent works: the context it reasons over, the models it runs, and what it carries across reviews.
Bet on where model capability is heading, and work with model labs and research teams to turn it into better reviews.
Define what a great AI review is, and hold the product to it with offline evals, online experiments, and production evidence.
Own the quality of the end-to-end review experience across VS Code, the GitHub Copilot app, and the GitHub Copilot CLI, and pull requests.
Own the reliability of a high-throughput service running at GitHub scale, including the on-call rotation.
Mentor senior and staff engineers, collaborate across disciplines, and help steer the team and product, all while staying hands-on: experimenting, shipping code, and building evals.
Work at the frontier of how software gets built with agents and evolve workflows that make the whole team faster.