AI Cybersecurity Team Lead, DeepMind

Deep Mind Mountain View, CA, USA ;
San Francisco, CA, USA

• PhD degree in Computer Science, a related field, or equivalent practical experience.
• 6 years of experience in cybersecurity research including cybersecurity exploitation, defenses for cyberattacks, and code security.
• 2 years of people management experience leading a research team.
• One or more accepted scientific publication submissions for conferences, journals, or public repositories (such as Usenix Security, IEEE SP, NeurIPS, ICML, ICLR, etc.).

• Experience with Python or C++.
• Experience working with Large Language Models (LLM’s) or applied AI.
• A deep passion for AI technology and all of its possibilities.

As an organization, Google maintains a portfolio of research projects driven by fundamental research, new product innovation, product contribution and infrastructure goals, while providing individuals and teams the freedom to emphasize specific types of work. As a Research Scientist, you'll set up large-scale tests and deploy promising ideas quickly and broadly, managing deadlines and deliverables while applying the latest theories to develop new and improved products, processes, or technologies.

From creating experiments and prototyping implementations to designing new architectures, our research scientists work on real-world problems that span the breadth of computer science, such as machine (and deep) learning, data mining, natural language processing, hardware and software performance analysis, improving compilers for mobile platforms, as well as core search and much more.

As a Research Scientist, you'll also actively contribute to the wider research community by sharing and publishing your findings, with ideas inspired by internal projects as well as from collaborations with research programs at partner universities and technical institutes all over the world.

AI's cyberattack capability is increasing rapidly; recently, there have been a number of publicized zero-day exploits found with the help of AI in well-tested software. Our team's mission is to detect if users misuse an AI model for the purpose of a cyberattack, and on enabling the model to refuse gracefully in such cases. Given the dual use nature of AI tools, the goal of this project is to advance the model's ability to discern between malicious and benign use.

Artificial intelligence will be one of humanity's most transformative inventions. At Google Deep Mind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority.

We are pushing the boundaries across multiple domains. Our global teams offer learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort.

The US base salary range for this full-time position is $262,000-$365,000 + bonus + equity + benefits. Our salary ranges are determined by role, level, and location. Within the range, individual pay is determined by work location and additional factors, including job-related skills, experience, and relevant education or training. Your recruiter can share more about the specific salary range for your preferred location during the hiring process.

Please note that the compensation details listed in US role postings reflect the base salary only, and do not include bonus, equity, or benefits. Learn more about benefits at Google.

• Lead the cyberattack safety team dedicated to preventing the malicious misuse of AI models while simultaneously advancing Gemini's proactive cyber defense capabilities.
• Oversee defense strategies across the entire technical stack, from in-model training and out-of-model classifiers to the architecture of holistic production defense systems.
• Translate systematic, innovative, and deep security research into rapid, real-world deployment—shipping solutions directly into models, peripheral…