Daniel Jones
Principal AI Safety Researcher
About
Daniel is a Principal AI Safety Researcher in the AI Red Team at Microsoft. In this role, he conducts long-term operations and research to assess and improve the safety of AI models and applications. His work involves discovering and exploiting vulnerabilities in Responsible AI systems, developing scalable methodologies for AI Red Teaming, and collaborating across disciplines to mitigate risks and inform best practices.
Daniel has a passion for privacy-preserving machine learning and AI security. His career spans multiple industries, including finance and pharmaceuticals, where he worked as a data scientist before joining Microsoft. He holds a PhD in Mathematics from Durham University, UK, where he studied algebraic invariants of knots in low-dimensional topology.