Senior Software Engineer, OpenAI Codex, Claude Code, Cursor

This is a fully remote position, open to applicants anywhere in the world.

📋 Description

• Evaluate the end-to-end interactions generated by AI in coding.

• Determine whether the outputs are useful, accurate at a high level, and consistent with robust engineering judgment.

• Analyze explanations and reasoning, not just the code itself.

• Differentiate between various levels of response quality.

• Provide clear, opinionated written feedback on what was successful, unsuccessful, or potentially misleading.

• Assist in defining what exceptional interaction looks like for Cursor, Codex, and Claude Code.

• Create short video explanations of evaluations.

• Engage in projects that last approximately two weeks to a few months.

⛳️ Requirements

• Senior, Staff, or Principal-level software engineer, or comparable experience.

• Strong proficiency in TypeScript/JavaScript or Python.

• Hands-on experience with at least one of OpenAI Codex, Claude Code, or Cursor.

• Extensive familiarity with modern AI-assisted development workflows.

• Ability to assess code without executing it or reviewing each line in detail.

• Strong written and spoken English proficiency at B2 level or higher.

• Comfortable providing direct, opinionated feedback.

• High standards for engineering quality.

• Nice to have: prior exposure to prompt design or evaluation workflows.

• Nice to have: experience in mentoring senior engineers or defining engineering standards.

• Must complete a take-home evaluation exercise accompanied by a recorded Loom walkthrough.

• Simple background check required.

🏝️ Benefits

• Flexible hours, 10–20 hours per week.

• Continuous project opportunities for evaluators who excel.

• Remote work available worldwide, subject to regional client eligibility.

• Start as soon as the take-home is successfully completed and a project seat is available.