Research Fellow(UK visa sponsorship available)
Job Description
About the Project
This project focuses on applying machine learning and AI methods to prostate cancer imaging. The goal is to use multiparametric MRI scans to predict the risk, presence, progression, and location of prostate cancer.
The successful candidate will join the UCL Department of Medical Physics and Biomedical Engineering, part of the UCL Hawkes Institute, which provides advanced computational facilities and a strong multidisciplinary research environment.
The department hosts internationally leading research groups, spanning physics, engineering, computer science, mathematics, and medicine, and offers a vibrant community for scientific collaboration and learning.
About the Role
We are seeking a Research Fellow to develop advanced computational tools for medical image analysis, with a focus on prostate cancer.
Key responsibilities include:
Designing and implementing deep learning algorithms for MRI analysis (segmentation, registration, multimodal data integration)
Curating and managing clinical imaging datasets
Developing software for disease modelling and image registration
Conducting independent, high-quality research and publishing in leading journals
Presenting work at conferences and contributing to grant writing
Supervising and mentoring junior researchers
Supporting interdisciplinary collaborations across physics, engineering, and clinical science
The post is initially funded for 12 months.
Candidate Requirements
Essential:
PhD (or equivalent research degree) in Mathematics, Engineering, Computer Science, Physics, or related field
Appointment at Grade 7 (£44,480+) requires award of PhD
Candidates awaiting thesis submission will be appointed at Grade 6B (£39,148 – £41,833), with promotion to Grade 7 backdated once the PhD is awarded
Strong research track record with first-author publications in peer-reviewed journals
Proven experience developing machine learning algorithms for medical imaging
Skills in Python and/or C++ programming
Experience with deep learning frameworks such as TensorFlow or PyTorch
Knowledge of computational disease modelling
Desirable:
Experience handling real-world clinical data
Expertise in image registration, multimodal fusion, or clinical decision support systems
Experience with histopathology, radiology, or related datasets
Evidence of contributing to interdisciplinary or translational research projects
Personal qualities:
Ability to work independently and collaboratively
Strong communication skills for presenting, publishing, and team interaction
Commitment to advancing AI for clinical impact
Visa information: This role is eligible for a Skilled Worker visa or Global Talent visa. UCL welcomes international applicants.
What We Offer
41 days’ holiday (27 annual leave + 8 bank holidays + 6 closure days)
Option to purchase 5 additional days of annual leave
Defined benefit CARE pension scheme
Cycle to Work scheme and season ticket loan
Immigration and relocation support (where applicable)
On-site nursery and gym facilities
Enhanced maternity, paternity, and adoption pay
Employee Assistance Programme (Staff Support Service)
Discounted medical insurance
More details: UCL Rewards and Benefits
Equality, Diversity, and Inclusion
UCL values diversity as a driver of innovation. We are committed to equality of opportunity, inclusivity, and ensuring our staff community reflects global talent.
We particularly encourage applications from candidates underrepresented in higher education, including people from Black, Asian and minority ethnic backgrounds, disabled people, LGBTQI+ individuals, and women in senior research roles.
Read more: UCL Equality, Diversity and Inclusion
How to Apply
To apply, please submit:
An online application form
A CV
A Cover Letter demonstrating how you meet the essential and desirable criteria (upload this under the “cover letter” section of the application form).
Note: If you provide a cover letter, you may leave blank the “Why you have applied for this role” box on the online form.
This rewritten version keeps all the key details but presents them in a structured, reader-friendly way that would work well both internally and on job boards.
