Senior Software Engineer – OpenAI Codex, Claude Code, Cursor

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

📋 Description

• Assess AI-generated coding interactions from start to finish.

• Evaluate whether the outputs are beneficial, accurate at a high level, and consistent with sound engineering judgment.

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

• Differentiate between various levels of response quality.

• Deliver clear, assertive written feedback regarding what was effective, what was not, and what seemed misleading.

• Assist in defining the ideal outcomes when collaborating with Cursor, Codex, and Claude Code.

• Produce brief video explanations.

• Begin as soon as the take-home assignment is completed and a project has an available position.

⛳️ Requirements

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

• Strong proficiency in TypeScript/JavaScript or Python.

• Practical experience with at least one of OpenAI Codex, Claude Code, or Cursor.

• Extensive knowledge of modern AI-assisted development workflows.

• Capable of evaluating code without executing it or scrutinizing every line.

• Excellent written and spoken English (B2 or higher); detailed written feedback and concise video explanations are essential.

• Comfortable providing direct, opinionated feedback.

• Maintains high standards for engineering quality.

• Prior experience with prompt design or evaluation workflows (preferred).

• Experience in mentoring senior engineers or establishing engineering standards (preferred).

• Must complete and successfully pass a take-home evaluation task with a recorded Loom walkthrough.

• Must consent to a straightforward background check for the project.

🏝️ Benefits

• Flexible working hours, ranging from 10 to 20 hours per week.

• Continuous project opportunities for evaluators who excel.

• Chance to engage in projects that last from approximately two weeks to several months.

• Remote work arrangement available globally.