C# Engineer, AI Code Reviewer

Role overview A short-term contract opportunity for a highly experienced engineer to assess how AI coding assistants behave in realistic scenarios. Rather than producing production code, the work centers on judging whether model responses reflect strong engineering judgment, useful reasoning, and an interaction style that builds trust with developers. The focus is on engineering taste and quality calibration across tools like OpenAI Codex, Claude Code, and Cursor-style AI-first IDEs.

Responsibilities

- Evaluate AI-generated coding interactions end-to-end and rate overall quality - Judge whether outputs are useful, broadly correct, and aligned with how a seasoned engineer would reason - Assess the quality of explanations, preambles, and chain-of-thought, not just the resulting code - Distinguish between quality tiers and articulate why one response is meaningfully better than another - Provide direct, opinionated written feedback describing what worked, what missed, and what felt misleading - Contribute to defining what a high-quality interaction looks like inside modern AI-assisted development workflows

Requirements

- Staff- or Principal-level engineering background, or equivalent real-world depth - Strong hands-on experience in TypeScript/JavaScript or Python - Direct working familiarity with OpenAI Codex, Claude Code, and AI-first IDEs such as Cursor - Deep understanding of contemporary AI-assisted development workflows and where they help or hurt - Ability to judge code quality without executing or line-by-line reviewing every snippet - Comfort making subjective but rigorous calls and giving candid feedback

Nice to have

- Prior experience with prompt design, model evaluation, or rubric-style review workflows - Background mentoring senior engineers or setting engineering standards across a team

Benefits and work setup

- Contract engagement with an ASAP start, running through early May with possible extension - Roughly 10–20 hours per week, suited to a fractional commitment alongside other work - Hourly rate of $100–$200, commensurate with senior-level expertise - Remote, async-friendly evaluation work with a lightweight hiring process: one take-home exercise followed by a single behavioral interview