🛠 Tech Stack

💼 About This Role

You'll help train large language models to write production-grade code by ranking, repairing, and refactoring AI-generated snippets. Your feedback will be injected into an RLHF pipeline that tunes models toward high-quality code that you'd actually ship.

🎯 What You'll Do

• Compare and rank multiple code snippets, explaining which is best and why
• Repair and refactor AI-generated code for correctness, efficiency, and style
• Inject feedback into the RLHF pipeline and keep it running smoothly

📋 Requirements

• 3+ years of professional software engineering in Ruby
• Strong code-review instincts to spot errors and performance issues
• Extreme attention to detail and excellent written communication skills

✨ Nice to Have

• Constraint programming experience
• Prior RLHF or AI training experience

🎁 Benefits & Perks

• 🌍 Remote — work from anywhere in accepted locations
• 💵 Weekly pay via PayPal or Stripe
• 🕐 Flexible hours — minimum 15 hrs/week, up to 40+

📨 Hiring Process

Estimated timeline: 1-2 weeks · AI estimate

1. 1Application· 15 min
2. 2Identity verification· 1 day
3. 3Offer· 1 week

🚩 Heads Up

• Contractor role with no benefits
• Hours not guaranteed, project-dependent
• Low pay rate for senior profiles