Google DeepMind
Research Scientist, Reinforcement Learning, DeepMind
How your CV stacks up
Upload your CV to see how well it fits this job role
?%
Research Scientist, Reinforcement Learning, DeepMind
Research Scientist – Reinforcement Learning, DeepMind
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 techniques
- Preference-based learning
- Agentic systems
- Familiarity with modern research stacks (e.g., JAX/Flax or PyTorch) and experience scaling experiments.
- Strong experimental judgment, including:
- Selecting appropriate baselines
- Designing insightful ablations
- Comfort with:
- Scaling methodologies
- Evaluation techniques
- Diagnosing complex failure modes
- High agency and drive to:
- Push projects forward
- Prioritize effectively
- Take initiative
- Excellent communication skills, with a focus on clear and honest presentation of research results.
Reasons to use Rodeo
Start with a chat, not a search bar
Grad scheme, placement, apprenticeship? Not sure what you want yet — that's fine. Your agent talks it through with you and turns "I have no idea" into a shortlist.
It searches the market for you
Every day your agent scans the market matching roles against what actually matters to you, not just keywords on a CV.
Only hits
No noise. No "maybe this fits." Just roles with a clear explanation of why they're right — and where to focus when applying.
About the Role
As a Research Scientist at DeepMind’s Reinforcement Learning (RL) team—led by Tom Schaul—you will:
- Drive fundamental research, product innovation, and infrastructure goals with broad autonomy and flexibility.
- Prototype and deploy high-potential ideas quickly while adhering to rigorous methodologies.
- Contribute to cutting-edge work spanning neuromorphic AI, multi-model large systems, and foundational breakthroughs across:
- Machine & deep learning
- Natural language processing
- Search technology
- Human-AI collaboration
The RL team at DeepMind has made transformative contributions, including:
- DQN, AlphaGo, Rainbow, AlphaZero, MuZero, AlphaStar, and the latest generation of Gemini.
DeepMind is a pioneering AI lab dedicated to advancing safety-first AI research for societal and product impact. Our multidisciplinary teams tackle complex global challenges while fostering innovation through collaboration with institutions worldwide.
Get help with your application
Your very own career expert that helps elevate your application to the next level.
Key focus areas include:
- Scalable multi-agent systems for emerging applications.
- Proprietary hardware accelerating frontier AI research.
- Pioneering large multimodal models (LLMs, vector models, etc.).
Responsibilities
- Research design: Propose and test novel hypotheses in reinforcement learning.
- Implementation: Develop algorithms and conduct end-to-end experiments, iterating on findings.
- Evaluation: Design rigorous abulations and metrics to refine hypothesis testing.
- Infrastructure: Improve tools and frameworks for enabling new research directions.
- Communication: Share insights through publications, presentations, and internal write-ups, maintaining high research standards.
Commitment to Equity & Belonging
Google and DeepMind are committed to an inclusive workforce. We actively seek candidates from all backgrounds and support accommodations as needed. For details, visit Google’s EEO policy page or complete the Accommodation for Applicants form.
“It took my CV and asked me questions relevant to understanding what kind of jobs to suggest for me. Suggestions were almost perfect. Jobs were exactly what I’ve been looking for.”
Jessica, London
Skills
Location