TypeScript Engineer, AI Coding Agent Evaluator

G2i is seeking a highly experienced Senior or Staff-level TypeScript Engineer to join as an AI Coding Agent Evaluator. This unique, fully remote role focuses on assessing the quality of interactions with modern AI coding agents, evaluating whether their reasoning and output align with the standards of a top-tier software engineer.

Key responsibilities

• Evaluate AI-generated coding interactions end-to-end to determine if they reflect strong engineering judgment.
• Assess the quality of explanations and reasoning provided by models like Claude Code and OpenAI Codex.
• Provide clear, opinionated feedback on what makes an interaction useful, trustworthy, and effective.
• Help define the benchmarks for what constitutes high-quality AI-assisted development.
• Distinguish between varying levels of response quality to improve future model performance.

Requirements

• Staff or Principal-level engineering experience with a deep background in TypeScript or Python.
• Hands-on experience using AI-assisted development tools such as Cursor, Claude Code, or OpenAI Codex.
• Ability to make rigorous, subjective judgments on engineering taste and workflow quality.
• Comfortable providing direct, critical feedback on technical reasoning and communication.
• Familiarity with modern AI-assisted development workflows and engineering standards.

What we offer

• A fully remote, flexible engagement of 10–20 hours per week.
• The opportunity to shape the future of AI-assisted coding tools.
• Collaboration with a team focused on high-level engineering excellence.
• A clear, structured evaluation process including a take-home exercise and a behavioral interview.