Minimum qualifications:

• PhD in Machine Learning, or equivalent practical experience.
• 2 years of experience implementing algorithms within research codebases.
• Experience conducting research in reinforcement learning, including contributions to peer-reviewed publications.
• Experience designing and executing end-to-end experiments, including setup, analysis, and interpretation.

Preferred qualifications:

• Experience with advanced reinforcement learning topics, such as RL for sequence models, post-training, preference-based learning, or agentic systems.
• Familiarity with modern research stacks (e.g., JAX/Flax or PyTorch) and experience scaling experiments.
• Strong experimental judgment, including selecting appropriate baselines and designing insightful ablations.
• Comfort with scaling methodologies, evaluation techniques, and diagnosing complex failure modes.
• High agency and drive to push projects forward, prioritize effectively, and take initiative.
• Excellent communication skills, with a focus on clear and honest presentation of research results.

About the job

As a Research Scientist, you'll also actively contribute to the wider research community by sharing and publishing your findings, with ideas inspired by internal projects as well as from collaborations with research programs at partner universities and technical institutes all over the world.

DeepMind’s Reinforcement Learning (RL) team is a long-standing and tight-knit team of collaborative scientists and engineers, led by Tom Schaul. We address large-scale research issues in reinforcement learning. We design, refine, and scale RL algorithms and deliver meaningful scientific or product impact. Over the past decade, members of the RL team have been instrumental in building DQN, AlphaGo, Rainbow, AlphaZero, MuZero, AlphaStar, AlphaProof and Gemini.

Artificial intelligence will be one of humanity’s most transformative inventions. At Google DeepMind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority.

Responsibilities

• Propose and pursue novel research directions by formulating and testing hypotheses.
• Implement algorithmic ideas and conduct end-to-end experiments, analyzing results and iterating on findings.
• Design evaluations and ablations to answer key questions and drive research decisions.
• Build and improve infrastructure to enable research at scale.
• Communicate research findings through write-ups, presentations, and publications, while fostering a culture of high standards and constructive feedback.