Postdoctoral Research Associate for Deep Learning and Image, Audio and Video Processing

Full-Time, Fixed-Term (19 months)

Applications are invited for the post of Postdoctoral Research Associate in the Department of Computer Science, funded by Innovate UK. The project builds the collaboration between DDM Health Ltd., Coventry, and Department of Computer Science, Royal Holloway, University of London.

Cardiometabolic diseases, including type 2 diabetes, hypertension, dyslipidaemia, heart failure and stroke, are among the leading causes of illness and early death. They are strongly driven by high rates of overweight and obesity: in 2022, 64% of adults in England were overweight or living with obesity, and 29% were living with obesity. Excess weight is a major risk factor for type 2 diabetes and for the heart and circulatory complications that follow. Around 5.6 million people in the UK are living with diabetes, about 90% of whom have type 2 diabetes. High blood pressure is widespread: around 30% of adults in England have hypertension, and one in three - approximately 4.2 million people, are undiagnosed. Many people with serious cardiometabolic risk factors are therefore only identified when they present with a heart attack, stroke or other emergency.

Current risk assessment relies on clinic visits, blood tests and questionnaires. These tools work, but they are resource intensive, depend on people attending appointments and are not designed for low-burden, remote screening at scale. There are currently no tools in routine NHS use that analyse a person’s voice to help identify cardiometabolic risk.

This partnership aims to conduct voice-based risk detection for cardiometabolic disease with associated neurodegenerative conditions. It aims to develop novel deep learning algorithms, audio and vision transformers, and hybrid attention mechanisms, to detect dementia, Parkinson's disease (PD), diabetes, hypertension, heart failure, and stroke, by analysing voice patterns. Weakly supervised and zero/few-shot learning methods will also be exploited to classify unseen conditions without or with limited training samples, in order to tackle data sparsity issues.

Applicants should have the equivalent of a PhD degree from Computer Science with research expertise in machine learning, deep learning, audio/image/video classification, attention mechanisms, zero/few shot learning, and evolutionary algorithms. The Research Associate should have proficient programming skills in Python, MATLAB, and C++/Java. He/she should have good oral communication and academic writing skills. Relevant publication records would be advantageous. Applications from those who require a visa to work in the UK are welcomed.

In return we offer a highly competitive rewards and benefits package including:

• Generous annual leave entitlement
• Training and Development opportunities
• Pension Scheme with generous employer contribution
• Various schemes including Cycle to Work, Season Ticket Loans & help with the cost of Eyesight testing.
• Free parking.

The post is based in Egham, Surrey where the University is situated in a beautiful, leafy campus near to Windsor Great Park and within commuting distance from London.

The Research Associate is also expected to attend project meetings and training events in DDM Health Ltd. (Coventry).

For an informal discussion about the post, please contact Professor Li Zhang, on li.zhang@rhul.ac.uk.

Applicants are encouraged to send their CVs, abstract, outline of dissertations, & publications for any informal discussion.

For queries on the application process, the HR Department can be contacted by email at: recruitment@rhul.ac.uk

Please quote the reference: 0626-212

Closing Date:  23:59, 26 July 2026  

Interview Date: Friday 31 July 2026

Royal Holloway is committed to equality and diversity & encourages applications from all sections of the community. Read here about structures and initiatives around equality and diversity, including information on staff diversity networks.

Advert information