Senior AI Coding Agent Evaluator

G2i Inc.; Jacksonville (FL); Teletrabalho; USD 138 000 - 276 000; Tempo parcial

Resumo da oferta

G2i Inc. is seeking a Senior Software Engineer to assess how AI coding agents behave in real-world scenarios. You won’t write production code; you’ll judge usefulness, preamble, and engineering judgment in interactions with Codex, Claude Code or Cursor.

This remote, part-time role focuses on evaluating outputs, giving clear feedback, and helping define high-quality AI-assisted development standards. Start after a take-home; ongoing projects run 2 weeks to months.

Qualificações

• Senior, Staff or Principal-level engineer (or equivalent experience).
• Hands-on experience with at least one of Codex, Claude Code or Cursor.
• Deep familiarity with modern AI-assisted dev workflows.
• Able to evaluate code without executing it or reviewing every line.
• Strong written and spoken English (B2 or above).
• Comfortable giving direct, opinionated feedback.
• High bar for what good engineering looks like.

Responsabilidades

• Evaluate AI-generated coding interactions end to end.
• Judge whether outputs are useful, correct at a high level, and aligned with a strong engineer mindset.
• Assess the quality of explanations and reasoning, not just the code.
• Distinguish between levels of response quality (e.g., what makes something a 2 vs a 4).
• Give clear, opinionated feedback in writing on what worked, didn’t, or felt off.

Conhecimentos

Senior engineer

Staff/Principal

English (B2+)

AI workflows

Ferramentas

OpenAI Codex

Claude Code

Cursor

Descrição da oferta de emprego

G2i Inc. is seeking a Senior Software Engineer to assess how AI coding agents behave in real-world scenarios. You won’t write production code; you’ll judge usefulness, preamble, and engineering judgment in interactions with Codex, Claude Code or Cursor.

This remote, part-time role focuses on evaluating outputs, giving clear feedback, and helping define high-quality AI-assisted development standards. Start after a take-home; ongoing projects run 2 weeks to months.