Research Assistant in LLM for Fault Diagnosis of Energy Systems
University of Surrey – Mechanical Engineering Sciences
Location:
Guildford
Salary:
£13,844 per annum pro rata (0.4 FTE)
Hours:
Part Time
Contract Type:
Fixed-Term/Contract
Placed On:
8th December 2025
Closes:
18th December 2025
We are seeking a highly motivated Research Assistant in Large Language Models (LLMs) for Fault Diagnosis of Energy Systems to support an EPSRC Supergen Network+ in Artificial Intelligence for Renewable Energy project funded through the University of Warwick. This is an exciting opportunity to contribute to cutting-edge research at the intersection of Renewable Energy Systems, Artificial Intelligence (AI), and Prognostics and Health Management (PHM). You will work as part of the Energy Research Cluster at the School of Engineering, focused on developing next-generation, data-driven frameworks that improve the resilience and sustainability of renewable energy systems and infrastructure.
In this role, you will:
Develop LLM-based models for fault detection, diagnosis, and predictive maintenance of renewable energy systems.
Contribute to the design and implementation of advanced data pipelines integrating sensor data, maintenance logs, and domain knowledge.
Conduct experiments, evaluate model performance, and help establish best practices for LLM-enhanced prognostics.
Collaborate with industry partners to translate research outputs into practical tools.
Prepare scientific reports, contribute to publications, and present research findings at internal and external meetings.
Support ongoing project development, including dataset curation, documentation, and reproducible research workflows.
This is a part time role working 14.4 hours/week.
About you
The candidates will need to have:
A degree in Engineering, Computer Science, AI, Data Analytics, or a related field.
Strong programming skills in Python and familiarity with LLM frameworks.
Experience with machine learning, natural language processing, or time-series modelling.
A strong interest in applying AI to engineering and energy-system challenges.