Research Fellow in AI for Battery Modelling and Control

Job Title
Research Fellow in AI for Battery Modelling and Control
Job Reference
2808
Application Closing Date
31/07/2025
Division, Department
Research Division, Research Centre for E-Mobility and Clean Growth (ECG)
Salary
Competitive starting salary range from £37,099 up to £40,521 per annum (dependent upon experience) with the potential to progress. A discretionary range for candidates with exceptional experience can be discussed/considered
Mode
3 Year Fixed Term Contract, Full Time

Our Mission

Coventry University is a global Education Group that empowers students and communities to transform their lives and society through teaching, learning, research, and enterprise.

An ambitious and innovative university, our research is designed to have real-world impact on society and tackle global challenges through our 16 challenge-led, interdisciplinary research centres. We enable high performing research teams and future research leaders to thrive and make an impact locally, regionally, nationally, and globally

The Role

As a Research Fellow, you will collaborate with leading experts across three international labs-spanning Coventry University\’s Centres for E-Mobility and Clean Growth and Computational Science and Mathematical Modelling, and Stellenbosch University\’s Mathematical Modelling group in South Africa. This cross-continental partnership, based in the UK with mobility to South Africa, fosters pioneering, cross-disciplinary research that integrates AI, energy systems and advanced mathematics.

This position aims to advance the next generation of battery modelling and control strategies by combining Supervised Machine Learning and Reinforcement Learning. The objective is to significantly enhance battery performance and longevity. While conventional methods rely on either physics-based models or high-level state estimation, this project invites you to transcend these boundaries-developing novel, computationally efficient models grounded in real-world data, and leveraging RL to optimise performance, lifetime, or both.

Qualifications Required

PhD (or equivalent) or professional experience equivalent to a PhD demonstrating an ability to carry-out independent research with a 1st Class/2.1 Degree

Our Successful Candidate

We seek an ambitious researcher with a strong foundation in Bayesian theory, machine learning, and mathematical modelling. You should be confident in software development and capable of passing a programming test. Experience with battery systems, lab-based experimentation and reinforcement learning is highly desirable.

The Benefits

As a staff member of Coventry University, you will have access to a wide range of industry leading rewards and benefits which includes:

• Excellent Employers Pension Contribution
• 30 days Annual leave plus Bank Holidays
• New Holiday Purchase Scheme up to 5 additional days
• BUPA Cash Plan
• 50% off Tuition Fee\’s for staff dependants
• CU Reward Scheme – Discounts across a range of High Street/ Online Retailers
• Cycle To Work scheme

Our Culture

As a global Education Group, equality, diversity, and inclusion are embedded within the fabric of our organisation and are a key focus of our core values. We harness the power and potential of the diverse cultures, backgrounds, abilities, and experiences of our students, colleagues, and partners to create opportunities for all.

Full Job Description & Person Specification

Click here to view the full job description and person specification

Please note that in addition to the standard application form, applicants will be required to submit a research proposal outlining their proposed research plans and clarity of how the research proposal is positioned in the wider research context .

Click here to see the attached form.

Interviews week commencing 11th August 2025

We look forward to hearing from you!

Please enable JavaScript

Screen readers cannot read the following searchable map.
Follow this link to reach our Job Search page to search for available jobs in a more accessible format. #J-18808-Ljbffr