Go - Senior Backend Engineer, AI Coding Agent Quality
G2iRemotely
pythontypescriptjavascriptaicursorclaude codeopenai codexcode evaluation
Job Description
📋 Description
- Evaluate AI coding agents end-to-end in real-world scenarios
- Judge usefulness, correctness, and engineering judgment in outputs
- Assess explanations and reasoning quality for AI-generated code
- Distinguish response quality levels (e.g., 2 vs 4)
- Provide clear, opinionated feedback on what worked or didn’t
- Help define what great looks like with AI-first tools
🎯 Requirements
- Staff / Principal-level engineer or equivalent
- Strong background in TypeScript / JavaScript
- Python experience
- Hands-on experience with OpenAI Codex, Claude Code, Cursor
- Deep familiarity with AI-assisted dev workflows
- Ability to evaluate code without fully executing every line
🎁 Benefits
- Take-home evaluation exercise
- One behavioral interview
- Competitive contract rate and flexible hours
Back to all jobs