Senior Research Scientist - AI Safety

About the role

We are seeking a Senior Research Scientist to join our high-impact R&D. You will lead novel research that advances scientific understanding and fuels our ambition to build safe AI systems. This is a crucial opportunity to join a small, high-agency team conducting vital red teaming and evaluations for frontier models in sensitive areas like cybersecurity and national security. You'll shape the future of safe AI deployment in the real world.

What you'll be doing

• Owning and driving forward high-impact AI research themes in AI safety.
• Contributing to the wider vision and development of Faculty’s AI safety research agenda.
• Supporting Faculty’s positioning as a leader in AI safety through thought leadership and stakeholder engagement.
• Shaping our research agenda by identifying impactful opportunities and balancing scientific and practical priorities.
• Leading technical research within the AI Safety space, from concept to publication.
• Supporting the delivery of evaluations and red-teaming projects in high-risk domains, such as CBRN and cybersecurity, with government and commercial partners.

Who we're looking for

• You have a track record of working with high-impact AI research, evidenced by top-tier academic publications or equivalent experience.
• You bring proven experience or a clear passion for Applied AI safety, perhaps from labs, academia, or evaluation and red-teaming roles.
• You possess deep domain knowledge in language models and generative AI model architectures, including fine-tuning techniques beyond API-level implementation.
• You have practical machine learning experience, with a focus on areas such as robustness, explainability, or uncertainty estimation.
• You are proficient with deep learning frameworks (PyTorch, TensorFlow, or similar) and familiar with the HuggingFace ecosystem or equivalent ML tooling.
• You have demonstrable Python engineering experience to build and support robust research projects.
• You have the ability to conduct and oversee complex technical research projects and possess excellent verbal and written communication skills.

Our Recruitment EthosWe aim to grow the best team - not the most similar one. We know that diversity of individuals fosters diversity of thought, and that strengthens our principle of seeking truth. And we know from experience that diverse teams deliver better work, relevant to the world in which we live. We’re united by a deep intellectual curiosity and desire to use our abilities for measurable positive impact. We strongly encourage applications from people of all backgrounds, ethnicities, genders, religions and sexual orientations.