Software Engineer, AI (TypeScript)

About the position

Help train large-language models (LLMs) to write production-grade code across a wide range of programming languages. You will compare & rank multiple code snippets, explaining which is best and why. Additionally, you will repair & refactor AI-generated code for correctness, efficiency, and style. Your role will involve injecting feedback (ratings, edits, test results) into the RLHF pipeline and keeping it running smoothly. The end result is that the model learns to propose, critique, and improve code the way you do. The RLHF process can be summarized as: 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.

Responsibilities

• Train large-language models to write production-grade code.
• Compare and rank multiple code snippets, providing explanations for your choices.
• Repair and refactor AI-generated code for correctness, efficiency, and style.
• Inject feedback into the RLHF pipeline and maintain its functionality.

Requirements

• 3+ years of professional software engineering experience in TypeScript.
• Strong code-review instincts to spot logic errors, performance traps, and security issues quickly.
• Extreme attention to detail and excellent written communication skills.
• Ability to explain why one approach is better than another.

Nice-to-haves

• Experience in constraint programming.

Benefits

• Fully remote work from anywhere.
• Compensation ranging from $30/hr to $70/hr, depending on location and seniority.
• Minimum of 15 hours/week, with up to 40 hours/week available.
• Engagement as a 1099 contract.