Research Scientist Tech Lead, Contextual Security

Core responsibilities:

• Lead the existing team to address key challenges in contextual security with connections to prompt injection, from leading the fundamental research to providing solutions for key products.
• Manage a team of researchers with extensive background in security and machine learning, and grow the team to keep up with the rapidly evolving space of contextual security problems.
• Identify unsolved, impactful privacy & security problems present in generative models through auto-red teaming, with priorities guided by securing critical products and product features.
• Build post-training data and tools hypothesized to improve model capabilities in problem areas, test hypotheses through evaluations and auto-red teaming, and contribute successful solutions into Gemini and other models.
• Amplify impact by generalizing solutions into reusable libraries and frameworks for protecting agents and models across Google, and by sharing knowledge through publications, open source, and education.

This role advances AI safety by developing security and privacy solutions for generative models like Gemini, ensuring these technologies can handle sensitive user data responsibly and be deployed for widespread public benefit.

Required skills and experience:

• PhD in Computer Science or related quantitative field OR 5+ years of relevant experience.
• Demonstrated experience driving complex research projects in AI security, security, privacy or safety.
• Experience managing teams of ~5-10 individual contributors.
• Demonstrated experience driving complex projects to landing in production or adoption in open source (advantage).
• Demonstrated experience in adapting research outputs into impactful model improvements, in a rapidly shifting landscape and with a strong sense of ownership (advantage).
• Research experience and publications in ML security, privacy, safety, or alignment (advantage).
• Experience working on contextual security or prompt injection (advantage).

Compensation includes a US base salary range of $248,000 - $349,000 USD + bonus + equity + benefits. Google DeepMind values diversity of experience, knowledge, backgrounds and perspectives and is committed to equal employment opportunity and accommodation for disabilities or additional needs.