🛠 Tech Stack

💼 About This Role

You'll evaluate the quality of interactions with coding agents like OpenAI Codex and Claude Code, focusing on engineering taste. You'll judge whether responses reflect strong engineering judgment and provide opinionated feedback. This role offers a chance to define what great looks like for AI-assisted development.

🎯 What You'll Do

• Evaluate AI-generated coding interactions end-to-end
• Judge whether outputs are useful and aligned with strong engineering thinking
• Distinguish quality levels (e.g., 2 vs 4) in model responses
• Provide clear, opinionated feedback on what worked and what felt off

📋 Requirements

• Staff/Principal-level engineer or equivalent experience
• Strong background in TypeScript/JavaScript or Python
• Hands-on experience with OpenAI Codex, Claude Code, or Cursor
• Comfortable evaluating code without deep line-by-line review

✨ Nice to Have

• Experience with AI-first IDEs like Cursor
• Prior exposure to prompt design or evaluation workflows
• Experience mentoring senior engineers or defining engineering standards

🎁 Benefits & Perks

• 💰 $100–$200/hour rate
• ⏰ 10–20 hours/week flexible schedule
• 🚀 Remote work from anywhere
• 📅 Through early May with possible extension

📨 Hiring Process

Estimated timeline: 1-2 weeks · AI estimate

1. 1Take-home evaluation exercise· 2-3 hours
2. 2Behavioral interview· 45 min