Principal Research Scientist - AI Safety
Lead and shape the scientific research agenda for AI safety, focusing on large language models and safety-critical systems within a high-impact, research-driven team. Conduct and oversee cutting-edge research, publish in top-tier venues, and contribute to red-teaming and evaluation projects in high-risk domains such as CBRN and cybersecurity. Mentor researchers and help position the organisation as a thought leader in trustworthy AI development.