At Google DeepMind, 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.

Join the Privacy & Security Team at Google DeepMind and play a crucial role in creating innovative privacy-preserving technologies to protect Gemini and other GenAI-based agents!

GenAI models and agents are increasingly used to handle sensitive data on behalf of users. To ensure they operate securely, trustworthily, and reliably, we need to address many unsolved, impactful research problems. These include but are not limited to:

• Contextually-aware reasoning, coding, and tool-use capabilities that lead to information-sharing actions.
• Development of comprehensive privacy benchmarks focused on agentic capabilities.
• Adherence to privacy norms, even under adversarial prompting.
• New agent architectures that offer privacy-by-design in realistic deployment scenarios.

Artificial Intelligence could be one of humanity’s most useful inventions. At Google DeepMind, 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.

Drive privacy and security research from ideation to experimentation and transformative impact:

• Identify impactful, unsolved privacy and security research problems, inspired by the need to protect cutting-edge capabilities. Research novel solutions through literature reviews, offline and online experiments, and building prototypes and demos.
• Verify research ideas in the real world by initiating and collaborating with Gemini teams working on safety, evaluations, and related areas to implement new innovations.
• Amplify impact by generalising solutions into reusable libraries and frameworks for protecting Gemini and product models across Google. Share knowledge through publications, open source contributions, and education.

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

Ph.D. in Computer Science or a related quantitative field, or a B.S./M.S. in Computer Science or a related field with significant relevant experience.

In addition, the following would be an advantage: 

• Ability to independently drive new research ideas from conception and experimentation to production in a dynamic environment.
• Strong research experience and publications in ML security, privacy, safety, alignment, or model evaluation.
• Experience with JAX, PyTorch, or similar machine learning platforms.
• A proven track record of achieving research impact in collaborative, multi-team environments with senior stakeholders.

Closing date: Monday, 28th October at 9:00am GMT