G2i
·Quality Assurance
AI Interaction Evaluator (Codex / Claude Code)
About this role
Contract role evaluating AI coding agent interactions for OpenAI Codex and Claude Code. Requires senior+ engineering judgment to assess reasoning quality and 'engineering taste' rather than syntax correctness. $100-200/hour, 10-20 hrs/week through early May.
Must have
Staff or principal-level engineering experience or equivalent
Strong background in TypeScript, JavaScript, or Python
Hands-on experience using OpenAI Codex, Claude Code, or Cursor
Deep familiarity with modern AI-assisted development workflows
Ability to evaluate code without fully executing or deeply reviewing every line
Comfort giving direct, opinionated feedback
High bar for what good engineering looks like
Technologies
Responsibilities
Evaluate AI-generated coding interactions end-to-end
Judge whether outputs are useful and correct at a high level
Assess quality of explanations and reasoning, not just code
Distinguish between different levels of response quality
Provide clear, opinionated feedback on what worked and what did not
Help define what great looks like when interacting with tools like Cursor
Benefits
Recruitment process
Contract position at $100 to $200 per hour
Approximately 10 to 20 hours per week
Duration through early May with possible extension
Start ASAP
Hiring process includes take-home evaluation exercise and one behavioral interview
This is not a traditional engineering role and you will not be writing production code
Role focuses on engineering taste rather than syntax correctness
