About the Role
- The Autonomous Agents team is seeking Research Scientists to advance next-generation technologies for open-ended autonomous agents designed to assist, support, and supplement humans in their daily lives. The specific focus includes enhancing the fast online adaptation of state-of-the-art models for efficient knowledge compounding during inference in agentic tasks, learning from experience, and the continual consolidation of experience into model parameters through methods like distillation and reinforcement learning. Additionally, researchers will work on developing self-improvement methods that are robust to issues such as model collapse or reward hacking.
- At Google DeepMind, Artificial Intelligence is recognized as potentially one of humanity’s most useful inventions. The team, composed of scientists, engineers, and machine learning experts, is dedicated to advancing the state of the art in AI. They utilize their technologies for widespread public benefit and scientific discovery, collaborating on critical challenges while prioritizing safety and ethics.
- Within this team, Research Scientists are encouraged to lead or support research agendas aimed at producing practically applicable technological advances for human-oriented agents. The expectation is to conduct novel research aligned with ambitious long-term goals, maintaining a strong focus on methods and tools that offer short-term practical benefits. This approach emphasizes rapid iteration and refinement of solutions catering to real-world use-cases, providing a solid foundation for better understanding the research boundary in a fast-paced field.
Requirements
- 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.
- 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 next generation of 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 working with/designing environments.
- Experience with In-Context Learning, Continual Learning (either in the context of RL or LLM)
Qualifications
- 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, etc.).
- A curiosity about, or experience with research topics surrounding personalization, memory, reasoning, self-improvement, and safety.
- Experience with designing and evaluating agentic tasks.
Benefits
Not explicitly mentioned.