Research Scientist, AI Safety and Alignment, 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.

The Deep Understanding team at Google DeepMind focuses on understanding machine behavior, capabilities, and limitations to safely empower humans. Led by Principal Scientist Been Kim, our team works at the intersection of empirical science and practical engineering. We prioritize concrete safety wins over conventional paper-writing cycles. While we solve mid- and long-term safety questions for future frontier models, our day-to-day work is grounded in solving real vulnerabilities in live systems. We maintain a sustainable, high-trust research environment where independent thinking is expected, and success is defined by how safe and reliable our models are in the hands of real users.

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.

Individual pay is determined by factors including job-related skills, experience, and relevant education or training.

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

Learn more about benefits at Google . Responsibilities

• Drive project work by defining the data structure, framework, design, and evaluation metrics for research solution development and implementation. Identify timelines and obtain resources needed.

• Identify defined problems/gaps in existing technology and engage stakeholders and leaders to address them.

• Author research papers to share and generate impact of research results across function and in the research community.

• Identify new and upcoming research areas by interacting with potential external and internal collaborators. Help in developing long-term research strategy and plans to expand the impact of Google research.

• Help in growing research business by sharing research trends and best practices within the community.

Minimum qualifications:

• PhD in Computer Science, Machine Learning, Artificial Intelligence, Mathematics, Physics, or a related STEM discipline, or equivalent practical experience.

• 1 year of experience initiating, scoping, and executing research in AI safety, alignment, or mechanistic interpretability.

• Experience evaluating, steering, red teaming, or implementing empirical safeguards on Large Language Models (LLMs) or frontier systems.

• Experience in Python or C++, deep learning frameworks (e.g., JAX, PyTorch), and agentic workflows or tools.

• First-author publications at machine learning conferences (e.g., NeurIPS, ICML, ICLR, or COLM).

Preferred qualifications:

• Post-doctoral or industry experience driving prototype-driven safety projects, with recognized publications, seminal papers, or open-source research frameworks.

• Experience in interdisciplinary research bridging cognitive science, computer science, machine learning, and technological ethics to address systemic AI risks.

• Deep expertise in post-training alignment, reinforcement learning, reasoning models, and agentic or mechanistic interpretability to diagnose machine behaviors.

• Demonstrated track record of translating theoretical alignment and safety findings into scalable, production-grade mitigations on live frontier models.

• Exceptional technical communication skills with a proven ability to influence cross-functional engineering, product, and safety policy stakeholders.