Senior AI Interaction Evaluator (Codex/Claude Code) – Contract

G2i; United States; Remote; USD 138,000 - 276,000; Full time

Job summary

G2i is seeking a Senior AI Interaction Evaluator to assess AI coding agents (Codex/Claude Code) in real-world scenarios. You will judge usefulness, correctness, and engineering judgment without writing production code.

Role focuses on evaluating explanations and reasoning, not just code, and providing actionable feedback to define high-quality interactions with AI tools across 10–20 hours per week. Start ASAP, through early May with possible extension.

Qualifications

• Staff / Principal-level engineer or equivalent experience.
• Strong background in TypeScript/JavaScript or Python.
• Hands-on experience using OpenAI Codex, Claude Code, Cursor.

Responsibilities

• Evaluate AI-generated coding interactions end-to-end.
• Judge usefulness, correctness, and engineering judgment of outputs.
• Provide clear, opinionated feedback on what worked, what didn’t, and what seemed off.
• Help define what great interactions look like with AI coding tools.

Skills

Senior engineer

TypeScript/JavaScript

Python

Tools

OpenAI Codex

Claude Code

Cursor

Job description

G2i is seeking a Senior AI Interaction Evaluator to assess AI coding agents (Codex/Claude Code) in real-world scenarios. You will judge usefulness, correctness, and engineering judgment without writing production code.

Role focuses on evaluating explanations and reasoning, not just code, and providing actionable feedback to define high-quality interactions with AI tools across 10–20 hours per week. Start ASAP, through early May with possible extension.