Senior Software Engineer - AI Interaction Evaluator (Codex / Claude Code)

About the role

We are seeking a senior‑level software engineer to evaluate the quality of interactions with modern AI coding agents such as OpenAI Codex and Claude Code. This contract position focuses on assessing whether the model’s responses reflect the judgment of a strong engineer, rather than writing production code.

Key responsibilities

• Assess AI‑generated coding interactions end‑to‑end for usefulness, high‑level correctness, and alignment with strong engineering thinking.
• Judge the quality of explanations, reasoning, and preambles, not just the final code.
• Distinguish between different levels of response quality and provide clear, opinionated feedback.
• Help define standards for what “great” looks like when interacting with AI‑first development tools.
• Collaborate with the team to refine evaluation criteria and documentation.

Required profile

• Staff‑ or principal‑level engineer (or equivalent experience).
• Strong background in TypeScript/JavaScript or Python.
• Hands‑on experience with OpenAI Codex, Claude Code, and AI‑first IDEs such as Cursor.
• Deep familiarity with modern AI‑assisted development workflows.
• Ability to evaluate code without fully executing every line and to give direct, rigorous feedback.

Required skills

• TypeScript
• JavaScript
• Python
• OpenAI Codex
• Claude Code
• Cursor (AI‑first IDE)

What we offer

• Hourly rates up to $200 USD (US/Canada), $150 EUR (EU/Latam), $100 USD (other locations).
• 10–20 hours per week, remote contract work.
• Start ASAP with potential extension beyond early May.
• Take‑home evaluation exercise and one behavioral interview as part of the hiring process.