Artificial intelligence
10 Google DeepMind reinforcement learning researchers
These ten current and former Google DeepMind research scientists hold or held research roles at the company, with work on reinforcement learning. A reader can learn what reinforcement learning research at Google DeepMind involves from people who have done it.
Professionals to explore
01—10Abhinav Gupta
LinkedInExperience: Research Scientist · Google DeepMind
Research Scientist at Google DeepMind since September 2024, based in London; the profile describes work at the intersection of reinforcement learning and language, fine-tuning large language models with machine and execution feedback and building evaluation metrics. Previous roles include Doctoral Student at Mila (2018–2024) and research internships at Google and Microsoft.
Abram L. Friesen
LinkedInExperience: Senior Staff Research Scientist · Google DeepMind
Senior Staff Research Scientist at Google DeepMind since May 2026, based in London; the profile describes work on Gemini with a focus on reinforcement learning for reasoning, agentic behavior and model capabilities. The profile also lists a Staff Research Scientist row at Google DeepMind since January 2019. Previous roles include Graduate Research Assistant at University of Washington (2008–2017).
Aditi Mavalankar
LinkedInExperience: Research Scientist · Google DeepMind
Research Scientist at Google DeepMind since December 2022, based in London; the profile names reinforcement learning as the research area, with interest in how agents use their interactions with an environment to adapt, generalize and explore. Previous roles include Graduate Student Researcher at University of California San Diego (2018–2021).
Avi Singh
LinkedInExperience: Research Scientist · Google DeepMind
Research Scientist at Google DeepMind since April 2023, based in San Francisco, working on large language models; the profile names reinforcement learning for large language models as the research interest. Previous roles include Research Scientist at Google (2021–2023) and Graduate Student Researcher at University of California, Berkeley (2016–2021).
Bobak Shahriari
LinkedInExperience: Staff Research Scientist · Google DeepMind
Staff Research Scientist at Google DeepMind since November 2023; the profile describes recent work on online and offline RL fine-tuning of language and multimodal models, and earlier work releasing Acme, a framework for RL research. The profile also lists a Research Scientist row at Google DeepMind since January 2018. Previous roles include Data Analysis and Visualization Engineer at ThoughtExchange (2016–2017).
Matthew W. Hoffman
LinkedInExperience: Senior Staff Research Scientist · Google DeepMind
Senior Staff Research Scientist at Google DeepMind since March 2016, based in London; the profile describes work on systems for training large language models with online and offline reinforcement learning, and earlier work on systems for RL research in continuous-action domains. Previous roles include Postdoctoral Researcher at University of Cambridge (2013–2016).
Samuel Holt
LinkedInExperience: Research Scientist · Google DeepMind
Research Scientist at Google DeepMind since November 2025, based in London; the profile describes work on LLM agents and their learning dynamics, with a particular focus on reinforcement learning. Previous roles include PhD Candidate in Machine Learning at University of Cambridge (2021–2025) and Machine Learning Engineer and Software Engineer at Fifth Row Technologies (2019–2021).
Sherry Yang
LinkedInExperience: Staff Research Scientist · Google DeepMind
Staff Research Scientist at Google DeepMind since April 2023, based in Mountain View; the profile lists reinforcement learning, generative modeling, world models and agents as the areas of the current role. Previous roles include Research Scientist at Google (2018–2023), which the profile ties to Google Brain and machine learning research.
Yuchen Zhuang
LinkedInExperience: Research Scientist · Google DeepMind
Research Scientist at Google DeepMind since May 2025, based in the San Francisco Bay Area; the profile describes a focus on reinforcement learning and post-training, with an interest in language model agents that reason and plan. Previous roles include Applied Scientist at Amazon (2024) and Research Scientist Intern at Adobe (2023).
Zita Marinho
LinkedInExperience: Research Scientist · Google DeepMind
Research Scientist at Google DeepMind from 2020 to 2026; the profile describes being part of the Reinforcement Learning Team there. The profile also lists Assistant Professor at University of Lisbon since 2026. Previous roles include Senior Research Scientist at Priberam (2018–2020) and PhD Student at Carnegie Mellon University (2012–2018).
Choose the right perspective
Match the person's focus to your question, since reinforcement learning for language model post-training, RL algorithms and frameworks, reward learning and agent research each involve different work. Consider how long the person has been at the lab, since longer tenure shapes how they can compare earlier RL research with current work on large models.
Questions to take into the conversation
- 01How has reinforcement learning research changed as the focus moved toward large language models?
- 02What makes RL training of a large model hard to run reliably at scale?
- 03How do you decide whether a reward signal is good enough to train against?
Reaching Google DeepMind reinforcement learning researchers
How can I contact one of these Google DeepMind reinforcement learning researchers?
Pick one of the 10 people on this page and choose "Book a paid call", or describe your project to find others. You offer a fee for a 15-minute call or a written answer, Instant Expert finds the person's work email and sends the invitation, and they decide whether to accept. The list covers 1 company: Google DeepMind, based on profile data retrieved on October 8, 2026. Being listed here doesn't mean someone has agreed to take calls.
How much does it cost to reach Google DeepMind reinforcement learning researchers?
You choose the offer, starting at $5 per person. It includes Instant Expert's 20% fee, so an offer that pays the person $100 costs you $125. You're charged only when the person books the call or sends the answer.
What if they don't reply?
You pay nothing. Instant Expert sends follow-up reminders, and if the person hasn't booked or answered within 7 days, the request expires and any hold on your card is released. You can invite several of the 10 people on this list at once and cap your total spend, so you pay only for the ones who accept.
Can an AI agent ask one of these Google DeepMind reinforcement learning researchers a question?
Yes. An agent with a USDC wallet on Base can ask one question without an Instant Expert account. It names the person, for example by the LinkedIn URL on this page, and pays per ask over x402 (HTTP 402). The person answers in writing or by voice note, and if nobody answers within 7 days, the payment goes back to the wallet automatically. x402 docs
About this directory
This is a professional research starting point based on business profile data retrieved on . Titles and companies reflect that source snapshot and may describe past or present roles. Check the linked profiles for current details. Inclusion does not imply Instant Expert membership or availability.
Request a correction or removal