If you already build software with AI-assisted coding tools, this job puts that experience to work. You review end-to-end coding sessions for correctness, workflow and reasoning, and write clear feedback against a rubric.
What you will do
- Review end-to-end coding sessions made with AI-assisted developer tools.
- Judge each multi-step session for correctness, workflow soundness, reasoning and best practice.
- Write clear, rubric-based feedback on each session.
What you need
- 3+ years of professional software development.
- Hands-on experience with AI-assisted coding tools and agentic or spec-driven workflows, such as Cursor, GitHub Copilot, Claude Code or similar.
- Strong code-reading and debugging skills across full-stack or backend systems.
Nice to have: experience with Kiro or Amazon CodeCatalyst, prior work grading AI-generated code, and contributions to developer tooling.
Apply (opens in a new tab)