Postdoctoral Research Associate in AI for Battery Degradation and Safety

About the role

We invite applications for a Postdoctoral Research Associate (PDRA) to join the Process Dynamics group in the Department of Materials at the University of Oxford (www.materials.ox.ac.uk).

You will develop and implement advanced deep learning models to analyse multi-modal operando data from accelerated stress testing, with the aim of deriving quantitative indicators of state-of-health (SoH) and state-of-safety (SoS). The project will also involve designing frameworks that leverage lower-cost or lower-resolution data modalities to predict key performance metrics and failure characteristics.

This is a full-time, fixed-term post for 2 years, and is based at the Department of Materials, Begbroke Science Park, Mount, Yarnton, Kidlington OX5 1PF.

The Project

The research will centre on the analysis of complex datasets generated during accelerated stress testing (AST) under demanding conditions (e.g. high voltage, high rate, elevated temperature, and abuse scenarios). These datasets comprise multi-modal, multi-scale measurements, including time-resolved X-ray radiography and tomography, coupled with electrochemical and thermal data. The objective is to characterise and disentangle the interacting electrical, thermal, and chemical processes that underpin battery failure.

The position is part of a Prosperity Partnership between the University of Oxford and Fortescue Zero, co-funded by UKRI-EPSRC: “A Prosperity Partnership in Energy Storage for Decarbonisation between the University of Oxford and Fortescue Zero.” The programme seeks to position the UK as a global leader in research and development of high-power, high-energy, and durable batteries for heavy industry. The project brings together advanced multi-modal X-ray imaging and in-line artificial intelligence, enabling near real-time data interpretation and accelerating scientific insight.

About You

You will hold, or be close to completing, a doctorate in Materials Science, Physics, Engineering, or a closely related discipline.

You will be a materials or physical scientist with a strong track record in applying deep learning to computer vision problems, ideally within battery characterisation using multi-modal operando datasets.

Practical experience in the design, construction, and operation of experimental setups for imaging-based investigation, of battery behaviour under in situ or operando conditions is also essential.

You will have a strong publication record appropriate to your career stage and excellent communication skills, enabling you to present complex research to a range of audiences.

You will be highly organised, able to manage your own research priorities.

How to apply

You will be required to upload your CV and a supporting statement as part of your online application. Your supporting statement should list each of the essential and desirable selection criteria, as listed in the job description, and explain how you meet each one. CVs alone will not be considered. Please do not attach any manuscripts, papers, transcripts, mark sheets or certificates as these will not be considered as part of your application.

Only applications received online by 12.00 midday (BST) on Wednesday 15th April 2026 can be considered. Interviews are scheduled to take place at the Department of Materials during the week commencing Monday 4th May 2026 and you must be available on this date, either by Teams, Zoom or in person.