Reinforcement Learning for Frontier AI Models
Core
Developing cutting-edge reinforcement learning algorithms and environments to improve large language models (LLMs) for reasoning, instruction following, and agentic work.
Role type
Senior IC reinforcement learning engineer (LLMs)
Builds
Large-scale RL environments, training data, and evaluation metrics for post-training LLMs
Domain
Artificial Intelligence / Large Language Models
Deliverable
production ML models
Required skills
reinforcement learning algorithms, LLM training, RL environment creation, data curation, experiment design, software engineering
Preferred skills
scaling large AI systems, applying RL to AI agents
Technologies
Python, C++, C#, Java, JavaScript
Responsibilities
Work on data collection, evaluation, and reinforcement learning methods for models; Design hypotheses and experiment plans for rapidly iterating on model performance.
Seniority
Senior, hands-on IC