Senior AI Coding Evaluator — Remote, Part-Time

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

Job summary

G2i is seeking a Senior to Principal-level engineer to join as an evaluator of AI coding agents. You won't write production code; you'll assess model-generated interactions for usefulness, reasoning, and engineering judgment across real-world prompts and tasks.

Applicants should have deep TypeScript/JavaScript or Python experience, hands-on familiarity with Codex/Claude/Cursor, and excellent written English. This remote, contract role offers flexible 10–20 hours/week with competitive hourly pay.

Qualifications

• Senior, Staff or Principal-level engineer with deep hands-on experience.
• Strong background in TypeScript/JavaScript or Python.
• Excellent written English and ability to give clear feedback.
• Hands-on familiarity with AI coding tools like Codex, Claude Code or Cursor.

Responsibilities

• Evaluate AI-generated coding interactions end to end.
• Judge usefulness, high-level correctness, and engineering judgment.
• Assess explanations and reasoning quality, not just code.
• Provide clear, opinionated feedback in writing and video explanations.
• Help define what great looks like when using AI coding tools.

Skills

TypeScript/JavaScript

Python

English proficiency

Tools

OpenAI Codex

Claude Code

Cursor

Job description

G2i is seeking a Senior to Principal-level engineer to join as an evaluator of AI coding agents. You won't write production code; you'll assess model-generated interactions for usefulness, reasoning, and engineering judgment across real-world prompts and tasks.

Applicants should have deep TypeScript/JavaScript or Python experience, hands-on familiarity with Codex/Claude/Cursor, and excellent written English. This remote, contract role offers flexible 10–20 hours/week with competitive hourly pay.