Find your next role
Discover roles across ambitious teams
5,569 jobs
- More jobs
G2i
Staff Software Engineer (AI Evals)
Remote · United States · Contract · Senior level
$100–$200 / hour
About the role
Evaluate the quality of AI coding agents' interactions focusing on engineering judgment and reasoning. Provide clear feedback on AI-generated coding outputs and explanations.
What you’ll do
• Evaluate AI-generated coding interactions end-to-end. • Judge usefulness and correctness of outputs. • Assess quality of explanations and reasoning. • Provide clear, opinionated feedback. • Help define standards for great AI interactions.
What you’ll bring
• Staff or Principal-level engineer experience. • Strong background in Go, Python, Rust, or TypeScript/JavaScript. • Experience with OpenAI Codex, Claude Code, Cursor. • Familiarity with AI-assisted development workflows. • Comfortable giving direct, opinionated feedback.