Research Scientist/Engineer, Autonomous Security, DeepMind

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 setup 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.

We are building AI agents that operate autonomously in complex security environments. This requires equal parts ML research and security expertise: designing training pipelines, reward functions, and evaluation benchmarks grounded in realistic security scenarios, then deploying those systems in real-world settings.

In a given week, you might fine-tune a foundation model on multi-step exploitation trajectories, design a reward function that captures nuanced security reasoning, build a security-focused RL environment, or architect an evaluation harness that measures agent performance across offensive and defensive security tasks. You will own the full research and development process, from ideation to impact.

Artificial intelligence will be one of humanity’s most transformative inventions. At Google DeepMind, 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.

Responsibilities

• Learn from environment feedback, reward modeling for multi-step agent trajectories, and supervised fine-tuning on curated security datasets.
• Build and orchestrate AI agents, executing security workflows, and capturing structured observations to produce different training data at scale.
• Design benchmarks that span complex, multi-step offensive, defensive, and infrastructure tasks.
• Design and evaluate autonomous agent architectures for security tasks such as Multi-step planning, tool-use orchestration, and decision-making under adversarial conditions.
• Provide thought leadership on research at the intersection of cybersecurity and artificial intelligence.

Minimum qualifications:

• PhD degree in Computer Science, Computer Engineering, Cybersecurity, a related quantitative field, or equivalent practical experience.
• 2 years of experience with software engineering/ data science .
• 2 years of experience designing, building, and maintaining production-grade software applications using Python as the primary language.
• 2 years of professional or academic research experience applying machine learning models to cybersecurity domains (e.g., threat detection, network traffic analysis, vulnerability exploitation).
• 2 years of research experience utilizing at least one of the ML framework (e.g., PyTorch, JAX, or TensorFlow).

Preferred qualifications:

• Experience with autonomous agent systems, including tool use, function calling, multi-step planning, and agent evaluation methodology.
• Experience generating or curating large-scale datasets for training or evaluating AI/ML models, particularly in security or systems domains.
  
• Published research in cybersecurity, AI for security, or related fields.
  
• Track record of deploying ML/AI systems in production security or safety-critical environments.

Applicants in San Francisco: Qualified applications with arrest or conviction records will be considered for employment in accordance with the San Francisco Fair Chance Ordinance for Employers and the California Fair Chance Act.