Teams at G2i

Evaluate AI-generated coding interactions end-to-end, judging usefulness, high-level correctness, engineering judgment, explanations, and reasoning. Provide clear, opinionated feedback, distinguish quality levels, and help define standards for excellent AI-assisted developer interactions.

Contract senior engineer evaluates AI coding agent interactions (Codex, Claude Code) for engineering judgment, reasoning quality, usefulness, and alignment with strong developer practices; provides opinionated feedback and helps define high-quality interaction standards. ~10-20 hrs/week, $100-$200/hr, short-term through early May.

Evaluate AI-generated coding interactions (Codex/Claude Code) for engineering judgment, usefulness, high-level correctness, explanations, and developer experience. Provide opinionated feedback, distinguish response quality levels, and help define best practices for AI-assisted developer workflows.