Train large-language models (LLMs) to write production-grade code:
Compare & rank multiple code snippets, explaining which is best and why.
Repair & refactor AI-generated code for correctness, efficiency, and style.
Inject feedback (ratings, edits, test results) into the RLHF pipeline and keep it running smoothly. End result: the model learns to propose, critique, and improve code the way you do.
Generate code ➜ expert engineers rank, edit, and justify ➜ convert that feedback into reward signals ➜ reinforcement learning tunes the model toward code you’d actually ship.
What is Needed
4+ years of professional software-engineering experience.
Extreme attention to detail and excellent writing skills—most of the job is explaining why one solution is better than another. This requirement cannot be overstated!
You actually enjoy reading documentation and specs.
Proven ability to thrive in a fully asynchronous, low-oversight remote environment.
Strong code-review instincts: can spot logic errors, performance traps, and security issues quickly.
No prior RLHF or AI-training experience required.
You don’t need deep machine-learning knowledge—if you can review code and explain your reasoning, we’ll teach you the RLHF bits.
Logistics
Location: Fully remote (work from anywhere).
Hours: Minimum 15 hrs/week with the ability to work up to 40 hours per week
Engagement: 1099 contract
Straightforward impact, zero fluff. If this fits your profile, apply here.
Apply Now