Description
About Us Artificial Intelligence could be one of humanity’s most useful inventions. At 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.
The Role As AI agents become more capable and autonomous, they introduce an entirely new frontier of security challenges. This role is about setting the multi-year vision for the fundamental security paradigms required to ensure agents remain safe, aligned, and resilient against attack as they advance toward AGI. You will be the single-threaded product owner responsible for the strategy that addresses the full spectrum of agent-related threats, including Prompt Injection, Anti-Distillation, and other novel Threats against AI.
Your scope will also include defining the product roadmap for ensuring System Integrity and developing the foundations for long-term AGI Control. The "product" is the end-to-end security posture and resilience of our agentic systems. You will own and navigate the complex trade-offs between agent capability, research velocity, and security, influencing and aligning senior leadership across Google to chart our path for deploying trustworthy agents.
Key responsibilities
Define and own the multi-year vision, strategy, and roadmap for a portfolio of Agent Security initiatives. Lead the product definition and strategy to defend against a wide range of threats, including prompt injection, anti-distillation, and adversarial misuse. Define the product roadmap for long-term, scalable AGI Contro
Employer contacts (email/phone/telegram) are hidden from the public preview —
send your CV, and we will connect you directly.