Evaluate end-to-end interactions with AI coding agents focusing on usefulness, high-level correctness, engineering judgment, and quality of explanations. Provide clear, opinionated feedback, distinguish response quality levels, and help define standards for great interactions. Role is remote, part-time (10–20 hrs/week), contract through early May at $100–$200/hour. Requires staff/principal-level engineering experience and hands-on familiarity with tools like Codex, Claude Code, or Cursor.

Seeking a senior (staff/principal-level) software engineer to evaluate AI coding agent interactions end-to-end (focus on usefulness, high-level correctness, engineering judgment, and quality of explanations). Contract role (~10–20 hours/week), paid $100–$200/hour, start ASAP through early May; work involves subjective, rigorous assessments and providing clear, opinionated feedback rather than writing production code.