Help Train Large-Language Models

Assist in training large-language models (LLMs) to write production-grade code across various programming languages:

• Compare & rank code snippets with explanations on the best choices.
• Repair & refactor AI-generated code for accuracy and style.
• Inject feedback into the RLHF pipeline to maintain smooth operations.
• End result: The model learns to propose, critique, and improve code like you.

RLHF in One Line

Generate code ➜ Expert engineers review and edit ➜ Feedback converts into reward signals ➜ Reinforcement learning adjusts the model for deployable code.

What You’ll Need

• 4+ years of software engineering experience in Java
• (Constraint programming experience is a plus)
• Strong code-review skills to quickly identify logic errors and security issues.
• Attention to detail and communication skills.
• You must enjoy explaining why one approach is better.
• Enjoyment in reading documentation and thriving in a low-oversight environment.

What You Don’t Need

• No prior RLHF or AI training experience required.
• No deep machine learning knowledge needed; clear code review and critique skills suffice.

Tech Stack

Strong command of Java is required.

Logistics

• Location: Fully remote — work from anywhere.
• Compensation: $30/hr to $70/hr based on location and skills.
• Hours: Minimum 15 hrs/week, up to 40 hrs/week.
• Engagement: 1099 contract.

Straightforward impact, zero fluff. If this aligns with you, apply here!