The position is for a Software Engineer specializing in AI, focusing on training large-language models (LLMs) to write production-grade code.
Responsibilities include comparing and ranking multiple code snippets, explaining which is best and why.
The role involves repairing and refactoring AI-generated code for correctness, efficiency, and style.
The engineer will inject feedback (ratings, edits, test results) into the RLHF pipeline and ensure it runs smoothly, allowing the model to learn to propose, critique, and improve code effectively.
The process involves generating code, having expert engineers rank, edit, and justify it, converting that feedback into reward signals, and using reinforcement learning to tune the model toward deployable code.
Requirements:
Candidates must have 4 or more years of professional software engineering experience.
Extreme attention to detail and excellent writing skills are essential, as most of the job involves explaining why one solution is better than another.
A genuine enjoyment of reading documentation and specifications is required.
Proven ability to thrive in a fully asynchronous, low-oversight remote environment is necessary.
Strong code-review instincts are needed to quickly spot logic errors, performance traps, and security issues.
Benefits:
The position is fully remote, allowing candidates to work from anywhere.
There is flexibility in hours, with a minimum requirement of 15 hours per week and the ability to work up to 40 hours per week.
The engagement is structured as a 1099 contract, providing straightforward impact without unnecessary complexity.
