JavaScript Engineer, AI Code Reviewer

Role overview This contract engagement focuses on evaluating how modern AI coding agents behave in realistic developer scenarios. Rather than writing production code, the engineer judges whether model outputs reflect strong engineering judgment, useful reasoning, and trustworthy interactions for experienced developers.

Responsibilities - Review AI-generated coding interactions end to end and judge whether responses make sense, are useful, and align with how a senior engineer would think. - Assess the quality of explanations, preambles, and reasoning rather than just the resulting code. - Distinguish between levels of response quality and articulate what separates a weak answer from a strong one. - Provide direct, opinionated written feedback on what worked, what did not, and what felt misleading or off-target. - Help define quality standards and evaluation criteria for AI-assisted coding experiences, including tools like Cursor.

Requirements - Staff or Principal-level engineering background, or equivalent real-world experience. - Strong expertise in JavaScript or TypeScript, with the ability to evaluate code without needing to execute or line-by-line review everything. - Hands-on experience using modern AI coding tools such as OpenAI Codex, Claude Code, or Cursor. - Deep familiarity with AI-assisted development workflows and how developers actually use them. - Comfort making subjective but rigorous quality judgments and communicating them clearly. - High bar for what good engineering looks like in both code and conversation.

Nice to have - Experience with AI-first IDEs and similar developer tooling. - Prior exposure to prompt design, evaluation rubrics, or model review workflows. - Background mentoring senior engineers or setting engineering standards across a team.

Benefits and work setup - Contract engagement paid at $100 to $200 per hour. - Roughly 10 to 20 hours per week, starting ASAP through early May with possible extension. - Hiring process includes a take-home evaluation exercise followed by a single behavioral interview.