Research Scientist, Autonomous Agents — Reinforcement Learning

Snapshot

We are looking for Research Scientists to join the Autonomous Agents team to conduct research on next‑generation technologies that power increasingly open‑ended autonomous agents, enabling them to assist, support, and supplement humans in their daily personal and professional lives.

• Enhancing the fast online adaptation of state‑of‑the‑art models to efficiently compound knowledge at inference in agentic tasks, learning from experience.
• Continual consolidation of experience into model parameters using methods such as distillation and reinforcement learning.
• Development of self‑improvement methods robust to degeneracies such as model collapse or reward hacking.

Artificial Intelligence could be one of humanity’s most useful inventions. At Google Deep Mind, we’re a team of scientists, engineers, machine learning experts and more, working together to advance the state of the art in artificial intelligence. We use our technologies for widespread public benefit and scientific discovery, and collaborate with others on critical challenges, ensuring safety and ethics are the highest priority.

• Research Scientists are encouraged to lead and support a research agenda aimed at producing practically applicable technological advances in autonomous agents.
• We expect research scientists to conduct novel research according to ambitious long‑term agendas while maintaining a strong focus on methods and tools offering practical benefits in the short term, grounding research with rapid iteration and real‑world use‑cases.

• Participate in the ideation and development of new use‑cases and capabilities of human‑oriented agents, guided by current research.
• Partner with research engineers to develop ambitious prototypes for anticipated agent use‑cases, and design and implement evaluation protocols around these prototypes.
• Identify roadblocks and research challenges motivated by empirical study of existing methods’ failures or limitations on use‑case‑based evaluations, and develop novel technical or methodological solutions to overcome such obstacles and limitations.
• Identify sources of data, design and implement data collection processes (supported by research engineering partners), and conduct human annotation and evaluation campaigns to produce and evaluate strong baselines for each use‑case.
• Help identify, within Google Deep Mind’s broad portfolio of research projects, methods that could be adapted or tested against our evaluations, and collaborate with teams and individuals to provide grounding and evaluation for their research agendas.

In order to set you up for success as a Research Scientist, we look for the following skills and experience:

• A PhD in a technical field or equivalent practical experience; recent graduates are encouraged to work closely with senior researchers on high‑value projects.
• Experience in a research domain connected to the production of increasingly autonomous human‑oriented agents (e.g., LLM‑powered agents, RL/IL, NLP applications, evaluation design).
• A desire to produce next‑generation agentic systems capable of learning from and efficiently adapting to deployment in real‑world scenarios.
• A strong technical background in RL, Imitation Learning, Distillation, and designing/environments.
• Experience with In‑Context Learning, Continual Learning (either in RL or LLM).

In addition, the following would be an advantage:

• Strong end‑to‑end system building and prototyping skills.
• Experience with one or more of: fine‑tuning LLMs, running human data collection/annotation campaigns, self‑play, multi‑agent systems, meta‑learning, meta‑RL, and/or skill discovery.
• Experience with open‑ended learning, RL, and frontier methods for training LLMs (RLVR, RLHF, RLAIF, multi‑turn RL, multi‑agent interactions, reward function design and modelling).
• A curiosity about, or experience with, research topics surrounding personalization, memory, reasoning, self‑improvement, and safety.
• Experience with designing and evaluating agentic tasks.

Closing date:
Friday, 6th March 2026 at 10:00am GMT

At Google Deep Mind, we value diversity of experience, knowledge, backgrounds and perspectives and harness these qualities to create extraordinary impact. We are committed to equal employment opportunity regardless of sex, race, religion or belief, ethnic or national origin, disability, age, citizenship, marital, domestic or civil partnership status, sexual orientation, gender identity, pregnancy, or related condition (including breastfeeding) or any other basis as protected by applicable law.

If you have a disability or additional need that requires accommodation, please do not hesitate to let us know.