The position is for a TypeScript Software Engineer specializing in AI, specifically in code evaluation and training.
The role involves helping to train large-language models (LLMs) to write production-grade code across various programming languages.
Responsibilities include comparing and ranking multiple code snippets, explaining which is best and why.
The engineer will repair and refactor AI-generated code for correctness, efficiency, and style.
The role requires injecting feedback (ratings, edits, test results) into the RLHF pipeline to ensure it runs smoothly.
The end goal is for the model to learn to propose, critique, and improve code in a manner similar to the engineer's own approach.
The process involves generating code, having expert engineers rank and edit it, justifying their choices, and converting that feedback into reward signals for reinforcement learning.
Requirements:
Candidates must have 4+ years of professional software engineering experience in one or more of the following languages: Python, Java, JavaScript, TypeScript, Go, C++, PHP, COBOL, C, Ruby, or Rust.
Strong code-review instincts are essential, with the ability to quickly spot logic errors, performance traps, and security issues.
Extreme attention to detail and excellent written communication skills are required, as much of the role involves explaining why one approach is better than another.
Candidates should enjoy reading documentation and language specifications and thrive in an asynchronous, low-oversight environment.
No prior experience in RLHF (Reinforcement Learning with Human Feedback) or AI training is necessary.
Deep machine learning knowledge is not required; the ability to review and critique code clearly is sufficient.
Benefits:
The position is fully remote, allowing candidates to work from anywhere.
Compensation is up to $30 per hour.
The role offers flexible hours, with a minimum of 15 hours per week and up to 40 hours per week available.
Engagement is through a 1099 contract, providing straightforward impact without unnecessary complexities.
