Preference Model

Design and implement RL training environments to test LLM reasoning on machine learning and systems problems. Translate ML research papers into concrete training tasks and deliver work into production training runs.

The intern will be responsible for designing and building Reinforcement Learning (RL) environments specifically tailored to test Large Language Model (LLM) reasoning across machine learning, systems, and research problems. This involves writing production-grade Python code and translating complex ML concepts from research papers into concrete, reproducible training tasks using tools like Docker.