Evaluate AI coding agents such as Codex, Claude Code, and Cursor for engineering judgment, reasoning quality, usefulness, and correctness. Provide detailed written feedback, distinguish response-quality levels, define evaluation standards, and record short video explanations. This flexible remote contract requires strong software engineering experience, familiarity with AI-assisted development workflows, and the ability to make rigorous, opinionated judgments without reviewing every line of code.

Evaluate AI coding agents such as Codex, Claude Code, and Cursor for engineering judgment, response quality, reasoning, usefulness, and trustworthiness. Provide clear written and recorded feedback, distinguish quality levels, and help define standards for excellent AI-assisted development workflows. This is a flexible, remote contract role focused on evaluation rather than production coding.