Senior AI Coding Quality Evaluator (Remote)

G2i; Ireland; Remote; EUR 123,000 - 246,000; Full time

Job summary

G2i is seeking a senior software engineer to help evaluate interactions with AI coding agents. This is not a traditional coding role; you won't write production software but will judge how the model reasons and whether its outputs reflect engineering judgment.

You will assess AI-generated coding interactions end to end, provide written, opinionated feedback, and help define what great looks like when using tools like Codex, Claude Code or Cursor.

Qualifications

• Senior, Staff or Principal level engineer with TS/JS or Python.
• Hands-on with OpenAI Codex, Claude Code or Cursor.
• Strong written and spoken English (B2+) and ability to provide clear feedback.
• Deep familiarity with modern AI-assisted dev workflows.

Responsibilities

• Evaluate end-to-end AI-generated coding interactions.
• Judge usefulness, high-level correctness and engineering judgment.
• Assess explanations and reasoning, not just code.
• Distinguish between different quality levels of responses.
• Provide clear, opinionated feedback in writing.
• 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 software engineer to help evaluate interactions with AI coding agents. This is not a traditional coding role; you won't write production software but will judge how the model reasons and whether its outputs reflect engineering judgment.

You will assess AI-generated coding interactions end to end, provide written, opinionated feedback, and help define what great looks like when using tools like Codex, Claude Code or Cursor.