The Research Scientist role at DeepMind focuses on addressing security and privacy challenges in AI systems, particularly in the context of Gemini and agentic products. The team is dedicated to developing innovative solutions to safeguard foundational models against emerging vulnerabilities. As part of a pioneering AI lab, the scientist will engage in both theoretical research and practical applications, contributing to the wider research community. This position emphasizes collaboration with various teams to integrate security innovations into existing infrastructures.

• PhD degree in Computer Science, a related field, or equivalent practical experience.
• 4 years of experience with research agendas across multiple teams or projects.
• 3 years of experience designing and implementing benchmarking frameworks for machine learning models.
• 2 years of experience in security and privacy.
• One or more scientific publication submissions for conferences, journals, or public repositories.

• Drive research to safeguard Gemini’s flagship foundational models and agentic products against emerging vulnerabilities at a massive scale.
• Design, prototype, and evaluate novel defense mechanisms to protect models and agents from adversarial attacks, prompt injections, and contextual security threats.
• Translate theoretical research breakthroughs into practical, real-world security solutions for both training and inference pipelines.
• Work closely with core modeling, engineering, and Trust and Safety teams to seamlessly integrate security innovations into Gemini's infrastructure.
• Stay ahead of the threat landscape by inventing next-generation security techniques specifically designed for autonomous and agentic AI systems.

• Employees at Google are often offered benefits like comprehensive health insurance, 401(k) matching, and flexible work arrangements, among other benefits.