This is an exciting opportunity for a software engineer or research associate interested in learning about machine learning and deep learning to join a collaborative project shared between King’s College London, the FMRIB centre, University of Oxford, and the Donders Institute, Nijmegen.
The post-holder will be responsible for developing and implementing novel algorithms and pipelines for surface mesh modelling; in particular, extending work on brain correspondence matching (https://fsl.fmrib.ox.ac.uk/fsl/fslwiki/MSM), using machine learning and/or discrete optimisation in order to improve the accuracy with which brain scans may be compared across individuals.
The overall aim of the award is to improve the translation of imaging into clinical practice by improving the precision with which imaging reflects biological processes, as well as designing more sensitive, interpretable, scalable, machine learning models for population analysis (and personalised trait prediction) in Big Data cohorts such as UK Biobank.
The project is jointly overseen by Dr Emma Robinson (KCL https://metrics-lab.github.io/) and Professors Saad Jbabdi, Steve Smith, Mark Jenkinson, Mark Woolrich, Karla Miller (Oxford), and Christian Beckmann (Nijmegen). Successful applicants will work under the supervision of two or more of the above, and in close collaboration with all the PIs on the grant.
The successful candidate will have a graduate degree in computer science or a closely related field. They will be able to demonstrate good software development skills with significant experience in C++ and Python, version control, software package release, support and management. In addition, we would look for experience in at least one of the following skills: machine learning, numerical optimisation, graphics or accelerated programming. Training in the relevant domains will also be provided through departmental courses, as well as collaborations with other developers and researchers.
This post will be offered on a fixed-term contract for 24 months (in first instance)
This is a full-time post – 100% full time equivalent
- Acceleration of existing C++ software implementations
- Incorporation of finite element/biomechanical models of tissue growth into tools for surface and volume matching
- Investigation of discrete optimisation and deep learning solutions to novel image registration problems
- Convert mathematical models to software
- Support and interact with researchers and clinicians to generate user friendly and clinically translatable software tools.
- Work closely with other software developers and promote software engineering best practice.
- Maintain accurate and up-to date technical and user documentation of the delivered software.
- Contribute to the dissemination of research through high-impact publications, open-source software and public engagement activities.
The above list of responsibilities may not be exhaustive, and the post holder will be required to undertake such tasks and responsibilities as may reasonably be expected within the scope and grading of the post.