University of Liverpool

Below is a list of prospective projects you can apply for, complete with a short explanation and the lead supervisor's name and department. Please contact them before making your application; you will be asked if you have done this on the application form.

If you are interested to learn more about a specific project before applying, download the full project proposal at the bottom of the page.

From Source to Speed: Evaluating Compilation Choices on Heterogeneous Cluster. Jianping Meng, IT Services

This project investigates how software compilation choices affect performance on a heterogeneous cluster with mixed CPU architectures and GPU‑equipped nodes. We will assess CPU targets, compiler families (GCC, AOCC, oneAPI, NVHPC), programming languages, and differences between pre‑built binaries and source‑compiled software. The results will provide practical guidance for building and managing applications on such systems. Interns will gain hands‑on experience with cluster environments, compilers, and performance evaluation while contributing to the research computing community.

HPC for All: Building Bridges to Untapped Computational Power. Manhui Wang, Research IT.

HPC usage is typically dominated by traditional user groups, such as Computer Science, Physics, Engineering and Chemistry. Computational research features ever more intensively over a wide scope of disciplines, but many UoL departments do not take advantage of the compute resources available to them. This may be due to a lack of experience or awareness of HPC, and perhaps some intimidation to explore further. This project is intended to break down barriers to HPC and inspire its adoption in new areas.

ChannelGate: A Gating Network to Route Ion-Channel Data towards Optimal Deep-Learning Models. Richard Barrett-Jolley, Musculoskeletal Biology

Our Deep-Channel web-app uses AI to decode noisy ion channel electrophysiology, accelerating analysis hundreds fold and removing manual bottlenecks in disease and drug research. A limitation is poor generalisation across protein families, forcing users to trial multiple pre trained models. We will create “ChannelGate”: a CNN that classifies incoming recordings, and selects the optimal Deep Channel model. HPC will enable rapid training and comparison of multiple model variants. Outputs: a Python prototype package ready for conversion to JavaScript and integration with our WebApp.

Machine Learning–Enabled Techno-Economic Analysis of Flexible Nuclear Power for Enhanced Renewable Integration in the GB Power System Chao Long, Electrical Engineering and Electronics

This project investigates how flexible operation of nuclear power plants can support higher renewable energy integration in the GB electricity system. Using historical electricity demand, renewable generation, electricity price and weather data, machine learning methods will be applied to identify patterns that influence grid balance and system flexibility. The project will simulate different scenarios with varying nuclear flexibility levels and nuclear capacity penetration in the generation mix. HPC resources will enable efficient processing of large time‑series datasets and rapid evaluation.

AI-Guided Discovery of Large-Band-Gap Dielectric Materials for Next-Generation Power Grids. Xue Yong, Department of Electrical Engineering and Electronics

In this project, you will explore how machine learning can be used to identify new dielectric materials for next-generation electronics. Using data from the Materials Project database, you will learn how to build machine-learning models that link chemical composition to electronic properties such as band gap. By combining data science, materials informatics, and computational modelling, you will create a predictive workflow and generate a simple “materials design map” highlighting promising candidates for high-voltage electrical insulation in future energy infrastructure.

Reinforcement Learning and Symbolic Transformer for Stability Certificates of Nonlinear Power Systems, Lin Jiang, Electrical Engineering and Electronics

This project develops an AI-assisted framework to automatically discover stability certificates for nonlinear power systems. As power grids increasingly rely on inverter-based renewable generation, system dynamics become highly nonlinear and difficult to analyse using traditional simulation or linear methods. The project combines reinforcement learning and symbolic transformer models to generate interpretable Lyapunov functions directly from system equations and evaluate them on power system models. Using HPC resources, the project will providing the student with practical training in HPC.

If you designed a project with a supervisor, please complete the application form with your project title.

You are given the opportunity to name the two projects you are most interested in. Please note that the projects from IT Services/Research IT are listed as possible to run, while the other four projects are scheduled to run. Therefore, please ensure that at least one of your selections is from outside of IT Services/Research IT. You are also welcome to choose both projects from outside of IT Services/Research IT if you would like.

This is what is required to complete the application form.

1. Your details (including full name, email, department, start and end dates of your degree course, and the expiry date of the current VISA for international students)
2. An uploaded PDF document that is no more than 3 pages long.
   

This document must include one A4 page stating the title of the project you are applying for, and answers to the following under these headings:

• Degree course and interest in the subject
• Motivation for applying for an N8 CIR internship
• What I hope to gain from completing the internship

You should follow this page with a CV of up to 2 pages, including the contact details of one referee.

This is all that is required to complete you application. Please do not send test submissions through the form.

Your uploaded file should be named: "YourSurname_initials_Liverpool.pdf" e.g., Other_AN_Liverpool.pdf

If you are having problems with your application, please contact us at enquiries@n8cir.org.uk

Applications will be assessed and successful candidates invited for interview.

Application deadline: 12 April, 2026

Shortlisting completed and students notified: w/c 20 April, 2026

Interview dates: w/c 27 April, 2026

Successful students notified: w/c 4 May, 2026