PhD research student to advance the science of measuring and mitigating machine learning risk and security.
This PhD-level research position supports advanced study into the risk, safety, and security of machine learning systems. The student will work alongside senior researchers to explore how ML models fail, how those failures can be measured, and how risk can be quantified and communicated to technical and non-technical stakeholders. The role blends rigorous academic research with applied outcomes — contributing to methodologies, benchmarks, and evidence that underpin trustworthy AI assurance.