Job Details

A company is looking for a Research Scientist, RL Training.Key ResponsibilitiesResearch and implement reinforcement learning techniques and translate them into data products for training large language modelsDesign and build data pipelines to generate high-quality training signals for reinforcement learning workflowsPrototype end-to-end RL training recipes and collaborate with teams to translate research into customer-ready data productsRequired QualificationsDeep expertise in reinforcement learning from human or AI feedback and reward modelingExperience training or fine-tuning large language models at scale, with knowledge of distributed training infrastructureStrong proficiency in Python and ML frameworks, particularly PyTorch and HuggingFaceSolid software engineering fundamentals for building research prototypesPh.D. in machine learning, reinforcement learning, or a related field strongly preferred; exceptional industry experience considered