Imperial College London
Closing soon
Top university
1 week ago
Research Associate in Backpropagation-Free Learning for Physical Neural Networks (Physics / AI) Imperial College London in United Kingdom
Degree Level
Postdoc
Field of study
Computer Science
Funding
Full funding availableDeadline
Aug 30, 2026
Country
United Kingdom
University
Imperial College London

How do I apply for this?
Sign in for free to reveal details, requirements, and source links.
Apply for this position
Keywords
Suggested positions
About this position
Research Associate in Backpropagation-Free Learning for Physical Neural Networks at Imperial College London, Department of Physics, South Kensington Campus (hybrid).
This post sits in Dr Jack Gartside’s group and focuses on physical neuromorphic computing across nanomagnetic, nonlinear nanophotonic, and nanoelectronic hardware. The project aims to develop backpropagation-free learning methods for training physical neural networks in situ, including contrastive learning, forward-forward and self-contrastive rules, and physical Kolmogorov-Arnold networks.
The role also involves building physics-aware surrogate models and digital twins (including neural ODEs), developing noise-aware and hardware-aware training, and helping close the sim-to-real gap for stochastic analogue devices. The successful candidate will lead the algorithmic direction of the project, publish in leading venues, present internationally, and contribute to follow-on funding bids.
Eligibility highlights: PhD awarded or imminent in physics, engineering, computer science, applied maths, or a closely related field; strong original work on backpropagation-free learning; experience with nanomagnetic, nanophotonic, and/or nanoelectronic hardware; scientific Python skills (PyTorch or JAX); and reproducible code release experience.
Funding and contract: salaried Research Associate role, £50,733–£59,484 per annum, full-time, fixed-term for 24 months. Candidates who have not yet been officially awarded their PhD may be appointed as a Research Assistant.
Deadline: 30 August 2026. The expected start date is 1 October 2026.
How to apply: Use the Imperial application portal linked in the advert. Submit your application early, as the vacancy may close before the stated deadline if there is high demand. For further details, contact Dr Jack Gartside at [email protected].
Funding details
Full funding including tuition fees and living expenses is available for this position. The scholarship covers all educational costs and provides a monthly stipend.
How to apply
Please submit your application including a cover letter, CV, academic transcripts, and contact information for two references. Applications should be sent via the online portal before the deadline.
More information can be found here
Ask ApplyKite AI

How do I apply for this?
Sign in for free to reveal details, requirements, and source links.