Senior Software Engineer, AI Coding Agent Evaluation

Contract remote role at 10-20 hours per week focused on evaluating the quality of interactions with coding agents such as OpenAI Codex, Claude Code and Cursor. No production code is written: you judge whether responses, explanations and reasoning reflect strong engineering judgment, delivering written feedback and short video walkthroughs. Requires a senior/staff/principal-level engineer with a strong TypeScript/JavaScript or Python background, hands-on use of those tools, and English B2 or above.

Source: Himalayas

Contentu does not verify employers. Never pay to apply for a job.