Senior AI Coding Evaluator & Taste-Maker (Remote)

g2i; United States; Remote; USD 138,000 - 276,000; Full time

Job summary

g2i is seeking a highly experienced software engineer to evaluate the quality of interactions with modern coding agents like OpenAI Codex, Claude Code and Cursor. This is not traditional production coding; you’ll judge whether the model thinks like a good engineer and whether the responses are useful.

You will assess how AI coding agents behave in real-world scenarios, focusing on accuracy, usefulness of preambles, and depth of engineering judgment, and you’ll provide clear feedback to help

Qualifications

• Senior, Staff or Principal-level engineer with a strong TS/JS or Python background.
• Hands-on experience with OpenAI Codex, Claude Code or Cursor.
• Excellent written and spoken English (B2+).

Responsibilities

• Evaluate AI-generated coding interactions end-to-end.
• Judge usefulness, correctness at high level, and engineering judgment.
• Assess explanations and reasoning, not just code.
• Provide clear, opinionated written feedback on what worked and what didn’t.
• Help define what great looks like when using AI coding tools.

Skills

TypeScript/JavaScript

Python

English communication

Tools

OpenAI Codex

Claude Code

Cursor

Job description

g2i is seeking a highly experienced software engineer to evaluate the quality of interactions with modern coding agents like OpenAI Codex, Claude Code and Cursor. This is not traditional production coding; you’ll judge whether the model thinks like a good engineer and whether the responses are useful.

You will assess how AI coding agents behave in real-world scenarios, focusing on accuracy, usefulness of preambles, and depth of engineering judgment, and you’ll provide clear feedback to help