G2i is seeking a senior-level software engineer (SR+) to evaluate AI coding agents like OpenAI Codex, Claude Code and Cursor. You won't write production code; you will judge whether the model demonstrates engineering judgment and useful explanations in real-world scenarios.
This remote contract role offers $100-$200/hour, 10-20 hours per week, with projects that run from two weeks to months. You must be fluent in English and provide transparent, opinionated feedback detailing what works and what feels