Senior AI Coding Evaluator (Remote)

G2i Inc.; Richmond (VA); Remote; USD 138,000 - 276,000; Part time

Job summary

G2i Inc. seeks a Senior-level software engineering evaluator to assess AI coding agents such as OpenAI Codex, Claude Code, or Cursor. This role focuses on judging model reasoning, usefulness, and engineering judgment in real-world tasks.

You will provide clear, opinionated feedback and Loom walkthroughs, helping define what great looks like for AI-assisted development. Remote, international, part-time contract work with 10-20 hours per week, starting as soon as you clear the take-home evaluation

Qualifications

• Must be a Senior, Staff or Principal engineer.
• Hands-on experience with OpenAI Codex, Claude Code or Cursor.
• Deep familiarity with AI-assisted dev workflows.
• Strong written and spoken English (B2 or above).
• Ability to give direct, opinionated feedback.

Responsibilities

• Evaluate AI-generated coding interactions end to end.
• Judge usefulness and high-level correctness of outputs.
• Assess explanations and reasoning, not just code.
• Provide clear, written feedback on what worked or misled.
• Help define what great looks like for AI tools.

Skills

Senior engineer

English proficiency

Feedback writing

AI workflows

Evaluation judgment

Tools

OpenAI Codex

Claude Code

Cursor

Job description

G2i Inc. seeks a Senior-level software engineering evaluator to assess AI coding agents such as OpenAI Codex, Claude Code, or Cursor. This role focuses on judging model reasoning, usefulness, and engineering judgment in real-world tasks.

You will provide clear, opinionated feedback and Loom walkthroughs, helping define what great looks like for AI-assisted development. Remote, international, part-time contract work with 10-20 hours per week, starting as soon as you clear the take-home evaluation