Research Scientist, Autonomous Agents

Research Scientist, Autonomous Agents — Reward Modelling

London, UK

We are looking for Research Scientists to join the Autonomous Agents team, and produce research in the development of next-generation technologies to power increasingly open-ended autonomous agents which strive to assist, support, and supplement humans in their daily personal and professional lives.

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.

This role will focus on research into developing next-generation reward models by analyzing the geometric and behavioral trajectories of multi-turn interactions to create highly adaptive and human-aligned autonomous agents.

A core focus will be mining implicit information from interaction dynamics to infer user state and enable the real-time adaptation and steering of AI agents. We will develop novel methodologies for capturing the success of complex multi-turn interactions, spanning both human-LLM and multi-agent scenarios. The majority of the work in this role will focus on rapid experimental iteration to quickly validate hypotheses and explore new research directions.

Within the team, Research Scientists are encouraged to lead/support a research agenda aimed at producing practically applicable technological advances in the ability of increasingly autonomous agents to assist, support, and empower humans.

The expectation is that research scientists will 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 as a form of pragmatic grounding. Central to this process is the idea that rapid iteration over and refinement of solutions catering to real-world use‑cases provides a strong basis for better understanding the research boundary in a fast paced field.

Participate in the ideation and development of new use‑cases and desired capabilities of human‑oriented agents of any form, advised by the current state of research.

Partner with research engineers to develop ambitious prototypes pertaining to desired or anticipated agent use‑cases, and design and implement evaluation protocols around these prototypes.

Identify, motivated by empirical study of existing methods' failures or limitations on use‑case‑based evaluations, the roadblocks and research challenges, 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 for the production and evaluation of strong baselines for each use‑case.

Help identify, within Google Deep Mind’s broad portfolio of research projects, methods which could be adapted or tried against our evaluations, as well as teams and individuals with which the team could partner to overcome challenges whilst providing grounding and evaluation for that collaborator's research agenda.

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. This specific role is targeting recent graduates, and the ideal candidate will be willing to work closely with one or more senior researchers on established high-value projects.
• Hands‑on experience with experiment design and analysis, including data collection and validation methodology, statistical analysis of results and their significance, and of performing rigorous ablation studies.
• Experience in a research domain connected to the production of increasingly autonomous human‑oriented agents, (e.g. LLM‑powered agents, RL/IL, applications in NLP, evaluation design).
• A desire to produce the…