Research Scientist in Reinforcement Learning

Job Summary

A company is looking for a Research Scientist, RL Training.

Key Responsibilities

• Research and implement reinforcement learning techniques and translate them into data products for training large language models
• Design and build data pipelines to generate high-quality training signals for reinforcement learning workflows
• Prototype end-to-end RL training recipes and collaborate with teams to translate research into customer-ready data products

Required Qualifications

• Deep expertise in reinforcement learning from human or AI feedback and reward modeling
• Experience training or fine-tuning large language models at scale, with knowledge of distributed training infrastructure
• Strong proficiency in Python and ML frameworks, particularly PyTorch and HuggingFace
• Solid software engineering fundamentals for building research prototypes
• Ph.D. in machine learning, reinforcement learning, or a related field strongly preferred; exceptional industry experience considered