Postdoctoral Research Assistant in AI Threat Detection

We are seeking

a full-time postdoctoral researcher to join the Machine Learning Research Group at the Department of Engineering Science (central Oxford). The post is funded by the Oxford Martin School and is fixed-term to the 31st August 2026. The successful candidate will work as part of a project team, consisting of researchers in the departments of Engineering and Computer Science, supporting the Oxford Martin Programme on AI Threat Detection, as well as engaging across the wide local network of experts in AI, cybersecurity, AI safety & governance. The Oxford Martin Programme on AI Threat Detection aims to fill a critical gap in AI security by developing advanced methods to detect attacks on AI systems. You will be responsible for developing a test framework including a library of target AI models and training datasets. You will also help research the spectrum of threat and vulnerability models for the AI systems. You should have a relevant PhD/DPhil or be near completion (submitted your thesis) together with relevant experience. You should also have previous experience with abnormality detection, or related machine learning techniques, for detecting unexpected patterns in large data sets. Only online applications received before midday on the 6th January 2025 can be considered.