Research Scientist, Reinforcement Learning

As a Research Scientist, you'll use machine learning knowledge and technical know-how to innovate, drive research projects, as well as apply research to impactful problems. You will be expected to implement code, run experiments, own results end-to-end, communicate them internally or externally, as well as collaborate with and empower others.

Your work may involve:

• Initiating or pursuing novel research directions, by proposing and testing research hypotheses.
• Implementing algorithm ideas and run end-to-end experiments, including setup, execution, analysis, and iteration.
• Sharing your skills and knowledge with other researchers.
• Building or improving infrastructure for research at scale.
• Designing evaluations and ablations that answer real questions and change minds.
• Analyzing results carefully, including debugging and failure analysis.
• Communicating clearly through plots, writeups, and paper-ready narratives and figures.
• Contributing to a culture of first-principles thinking, high standards, and direct, constructive feedback.

Our projects span the full range of state-of-the-art machine learning and AI fields, including large language models, distributed machine learning techniques, and much more, but with an emphasis on reinforcement learning.

We take a holistic view of people's backgrounds, and do not expect you to be an expert in all areas. We do expect you to proactively and quickly adopt new technologies and systems, but we also invest a lot of time in training and helping people to continually learn as part of their role.

• A passion for reinforcement learning
• A research track record in RL, including peer-reviewed publications.
• Strong implementation ability and comfort working in research codebases.
• Evidence of owning experiments end-to-end, including analysis and interpretation.
• Strong communication skills and a bias toward clarity and honesty regarding results.
• High agency and drive: You push projects forward, prioritize effectively, and take initiative.
• PhD in ML preferred, or equivalent practical experience.

• Experience with RL for sequence models, post-training, preference-based learning, or agentic systems.
• Experience with modern research stacks (e.g., JAX/Flax or PyTorch) and scaling experiments.
• Strong experimental taste: Good judgment regarding baselines, ablations, and what is worth testing.
• Comfort with scaling, evaluation methodologies, and diagnosing complex failure modes.
• A focus on craft: You care about doing excellent work while maintaining a high velocity.