Related skills
ai llm rlhf📋 Description
- Train LLMs to write production-grade code across languages
- Compare and rank code snippets, explain best option
- Repair/refactor AI-generated code for correctness and style
- Inject feedback into the RLHF pipeline and keep it running
- End result: model learns to propose, critique, and improve code
- RLHF in one line: Generate code → engineers rank/edit → reward signals → RL tunes toward ship-ready code
🎯 Requirements
- 3+ years in C++ software engineering (constraint programming bonus, not required)
- Strong code-review instincts to spot logic errors, performance traps, security issues
- Extreme attention to detail and clear written communication; explain why one approach is better
- Comfortable reading docs and language specs; work well in asynchronous, low-oversight environment
- Identity verification to work as an independent contractor in your country
- No prior RLHF or AI training experience
🎁 Benefits
- Fully remote — work from anywhere on the accepted locations list
- 1099 independent contractor engagement
- Weekly payment via PayPal or Stripe
- Flexible hours: 15–40+ hrs/week vary by project
Meet JobCopilot: Your Personal AI Job Hunter
Automatically Apply to Engineering Jobs. Just set your
preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.
Help us maintain the quality of jobs posted on Empllo!
Is this position not a remote job?
Let us know!