Postdoctoral Researcher in Machine Learning analysis of MRI

Cambridge University Hospitals NHS Foundation Trust
Cambridge, United Kingdom
3 months ago
Applications closed

Related Jobs

View all jobs
Spotlight

Forward Deployed Engineer

SolveAI London, United Kingdom
Hybrid
Spotlight

Senior ML Compiler Engineer

Fractile Bristol, United Kingdom

Data Scientist, Antibody Design (12-month

Relation Therapeutics London, United Kingdom
On-site

Research Scientist (Machine Learning), London

Isomorphic Labs London, United Kingdom

Research Scientist (Machine Learning), Lausanne

Isomorphic Labs United Kingdom

Research Associate* in Machine Learning Aided Data Compression and Communication

Imperial College London London, United Kingdom
£49 – £57 pa On-site

Research Scientist (Applied LLMs), London

Isomorphic Labs London, United Kingdom

Research Associate in Computer Vision

University of Oxford Oxford, South East England, United Kingdom
£39 – £43 pa Hybrid
Posted
5 Mar 2026 (3 months ago)

A Vacancy at Cambridge University Hospitals NHS Foundation Trust.


Postdoctoral Researcher in Machine Learning analysis of Magnetic Resonance Imaging (MRI)


Applications are invited for an enthusiastic and motivated Post‑doctoral Researcher to join the Lysosomal Disorders Unit at Cambridge University Hospitals NHS Foundation Trust. The post (Band 7) is funded by an award from industry, for a term of two years. The successful applicant will work as part of a team of clinical and imaging specialists.


The ethically‑approved award is to develop a machine‑learning technique to simulate quantitative Dixon fat/water images from a database of traditional T1 and T2‑weighted MR images of muscle. A large training set of Dixon fat/water images, paired with T1 and T2‑weighted images of muscle and other structures, is available locally and from collaborators. The ultimate purpose is to develop a technique to monitor disease progression and response to treatment in genetic diseases of muscle, in which fat replacement is a hallmark of disease. Such a technique may have wider application to other organs, tissues and disease states.


Requirements:



  • PhD in a relevant subject such as computer science or engineering.
  • Essential experience in advanced analysis of medical images, particularly machine‑learning analysis of musculoskeletal MR.
  • Experience in manual and machine‑learning segmentation of anatomic structures is highly desirable.
  • A substantial publication record in the field is valued.

Additional desirable skills:



  • Excellent organisational skills.
  • Ability to work as part of a team, as well as independently.

Key responsibilities are outlined in the attached Applicant Information Pack (combined Job Description and Person Specification).


Our Trust

Cambridge University Hospitals (CUH) NHS Foundation Trust comprises Addenbrooke’s Hospital and the Rosie Hospital in Cambridge. With over 13,000 staff and more than 1,100 beds the priorities of the Trust focus on a quality service that is all about people – patients, staff and partners. Recognised as providing “outstanding” care to our patients and rated “Good” overall by the Care Quality Commissioner, this is a testament to the skill and dedication of the people who work here. CUH’s values – Together – Safe, Kind, Excellent – are at the heart of patient care, defining the way all staff work and behave. The Trust provides accessible high‑quality healthcare for the local people of Cambridge, together with specialist services, dealing with rare or complex conditions for a regional, national and international population.


CUH is committed to promoting a diverse and inclusive community – a place where we can all be ourselves. We value our differences and fully advocate and support an inclusive working environment where every individual can fulfil their potential. We welcome applications for all positions in the organisation irrespective of people’s age, disability, ethnicity, race, nationality, gender identity, sex, sexual orientation, religion or belief, marriage and civil partnership status, or pregnancy and maternity status, or social economic background.


Benefits to you

At Cambridge University Hospitals, we want to do all we can to support good working days. We offer development opportunities and a wide range of benefits, including:



  • On‑site leisure facilities, shopping concourse and day nurseries.
  • Reduced‑cost Stagecoach bus travel to and from Cambridge University Hospital site.
  • Free park‑and‑ride bus journeys between Babraham Road and Trumpington sites, and the route to and from Cambridge train station and our hospitals.
  • Subsidised cost of parking on site for eligible staff.
  • On‑campus hot food available 24/7 and at a reduced cost for colleagues.
  • Staff pod break spaces with free tea and coffee, a break space and private outside area.
  • Flexible arrangements including part‑time working, job‑share, term‑time working and flexible start and finish times.

We welcome applications from the Armed Forces.


Informal enquiries can be directed to Dr. Patrick Deegan (). The vacancy will close at midnight on 9th March 2026. Interviews are due to be held on 26th or 27th March 2026.


#J-18808-Ljbffr

Industry Insights

Discover insightful articles, industry insights, expert tips, and curated resources.

Where to Advertise AI Jobs in the UK (2026 Guide)

Where to advertise AI jobs UK in 2026: the specialist boards and communities that reach AI engineers, ML scientists and applied research talent in the UK. The candidate pool is small, highly informed and in demand across multiple sectors simultaneously. General job boards reach a broad audience but lack the specificity that AI professionals expect — and the filtering mechanisms they rely on. Specialist platforms, direct outreach and academic channels each serve a different part of the market. This guide, published by ArtificialIntelligenceJobs.co.uk, covers where to advertise AI roles in the UK in 2026, how the main platforms compare, what employers should expect to pay, and what the data says about time-to-hire across different role types.