Senior Software Engineer – AI Interaction Evaluator (up to $200/hr)

About the role

We are seeking a senior‑level software engineer to evaluate how modern AI coding agents such as OpenAI Codex and Claude Code interact with developers. This contract position focuses on judging the quality of AI‑generated code, reasoning, and overall engineering “taste,” rather than writing production code.

Key responsibilities

• Assess end‑to‑end AI‑generated coding interactions for usefulness, correctness, and alignment with strong engineering judgment.
• Evaluate explanations, reasoning, and preambles to determine whether they aid or mislead developers.
• Distinguish between different quality levels of responses and assign consistent ratings.
• Provide clear, opinionated feedback on what works, what doesn’t, and what feels “off.”
• Help define standards for great interactions with AI‑first tools such as Cursor.

Required profile

• Staff‑ or principal‑level engineer (or equivalent experience).
• Deep experience with TypeScript/JavaScript or Python.
• Hands‑on use of OpenAI Codex, Claude Code, and AI‑first IDEs like Cursor.
• Ability to evaluate code and reasoning without fully executing every line.
• Comfort delivering direct, rigorous feedback and a high bar for engineering quality.

Required skills

• TypeScript
• JavaScript
• Python
• OpenAI Codex
• Claude Code
• Cursor (AI‑assisted development environment)

What we offer

• Hourly rate up to $200 (US/Canada), $150 (EU/Latam), $100 (other regions).
• 10–20 hours per week, remote work.
• Contract through early May with possible extension.
• Take‑home evaluation exercise and one behavioral interview.