Research Scientist/Engineer, Autonomous Security

About the job

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.

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.

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

US: $174000 - $252000 (USD) + 15% bonus target + equity + benefits

Learn more about benefits at Google.

Responsibilities

• Design and iterate on post-training methodologies for Gemini, including reinforcement learning from execution feedback, multi-step trajectory reward modeling, and supervised fine-tuning on curated security datasets.
• Build scalable simulated environments and synthetic data pipelines to execute complex security workflows and generate high-signal training trajectories at scale.
• Architect autonomous agent harnesses capable of multi-step planning, tool orchestration, and decision-making under adversarial conditions.
• Develop end-to-end evaluation benchmarks that measure frontier capability limits and trajectory fidelity across realistic offensive, defensive, and vulnerability tasks.
• Transition research innovations into Google's internal defenses and customer products, while contributing to technical reports and ML and security publications.

Qualifications

Minimum qualifications:

• PhD in Computer Science, Cybersecurity, ML, a related field, or equivalent practical experience.
• 4 years of experience in Python and ML frameworks (PyTorch, JAX, or TensorFlow) training, fine-tuning, and evaluating foundation models.
• 3 years of experience applying ML or automated reasoning to cybersecurity, systems, program analysis, or code generation.
• 2 years of experience in LLM post-training, including supervised fine-tuning, execution-feedback reinforcement learning, and multi-step trajectory reward modeling.

Preferred qualifications:

• Experience architecting autonomous agent systems, focusing on multi-step planning, tool orchestration, reward modeling, and reinforcement learning.
• Experience building scalable simulated execution environments, evaluation harnesses, or synthetic data pipelines for training and benchmarking foundation models.
• Deep domain expertise in one or more specialized cybersecurity areas, such as vulnerability discovery and automated patching, offensive security operations (red teaming), or advanced threat detection.
• Track record of published research at ML or cybersecurity venues, or a demonstrated history of deploying AI systems in production security environments.