About the role
We are seeking an ambitious and highly motivated Research Fellow in Computer Vision to contribute to an EPSRC-funded project, LungSight, focused on visual and acoustic screening for early detection of lung diseases.
Based in the Department of Computing and Mathematics, you will lead the design and development of AI-driven models applied to video and audio datasets, contributing to the creation of a low-cost, non-invasive screening tool for early diagnosis of chronic lung disease. LungSight's goal is to make respiratory screening accessible, affordable, and proactive—helping clinicians diagnose earlier and empowering patients to take control of their lung health.
You will work closely with an interdisciplinary team from six institutions: Professor Moi Hoon Yap (Manchester Metropolitan University), Dr Ning Ma (University of Sheffield), Professor Anna Barney (University of Southampton), Professor Bibek Gooptu (University of Leicester), Professor Akhilesh Jha (University of Cambridge), and Dr Oliver Price (University of Leeds). The project is also delivered in partnership with Asthma + Lung UK, Yorkshire Ambulance Service NHS Trust, South Yorkshire Digital Health Hub, Yorkshire & Humber Secure Data Environment, Foundation for Genomics and Population Health, Nvidia, NIHR Cambridge Biomedical Research Centre, Aberystwyth University, and ELAROS.
This is a unique opportunity to develop advanced AI methodologies to a real-world clinical challenge and to collaborate closely with computer vision, acoustic processing, and clinical expertise, and people living with lung disease.
Key Responsibilities
1. Lead the design and implementation of visual cues detection on video datasets (face and gesture), context-aware multimodal analysis, machine learning/self-supervised learning for automatically detecting subtle movement.
2. Contribute to the development of a multiple data source integration (visual and acoustics) for early detection of lung diseases.
3. Develop and optimise scalable data processing pipelines, including GPU acceleration, cloud computing, and distributed architectures, to enable efficient analysis of large-scale video datasets.
4. Collaborate with clinical and academic collaborators, external partners, to ensure scientific rigour, clinical relevance, and impactful interdisciplinary outcomes.
5. Produce and disseminate high-quality research outputs, including peer-reviewed publications, conference presentations, and engagement with stakeholders; contribute to the preparation of research funding proposals.
6. Engage in scholarly development and network-building, supporting your own academic career progression while enhancing the University's research culture and collaborative profile.
7. keep relevant stakeholders updated on progress, and be responsible for exploring their needs and acting on feedback, in order to ensure that research delivers against their requirements.
Qualifications:
8. APhD in Computer Science/Computer Vision/AI or a closely related field.
9. Extensive research experiencein machine learning, deep learning, and self-supervised learning, with a strong track record of applying these techniques to video datasets, in healthcare or other challenges.
10. Demonstrable expertise in processing and analysinglarge-scale, multimodal datasets (e.g. video, acoustics, clinical records) for predictive modelling and decision support.
11. Proficiency in programming languages such as Python (and/or Java, C/C++), with hands-on experience using deep learning frameworks (e.g. PyTorch, TensorFlow) and relevant libraries.
12. Practical experience inscalable data processing, including the use of parallel computing, cloud platforms,and distributed systems for efficient, high-volume data analysis.
13. Astrong publication record in high-impact peer-reviewed journals and international conferences, evidencing independent and original research contributions.
14. Proven ability to work withininterdisciplinary research teams, including collaborations with clinical or healthcare professionals.
15. Excellent written and verbal communication skills, including experience in presenting complex research findings to academic and non-academic audiences.
Desirable:
16. Knowledge offace and gesture analysis, multimodal integration, or subtle / micro-movement analysis. Experience with context-aware multimodal deep learning.
17. Experience with research funding, including contributing to or leading successful grant applications.
18. Experience in supervising or mentoring postgraduate students or junior researchers.