Fixed-term: The funds for this post are available for 9 months in the first instance.
Role Summary
We seek to appoint a Research Assistant to contribute to a research programme developing data-driven and AI-based methods for improving the energy efficiency of buildings and reducing their carbon footprint.
Decarbonising heat in the UK's existing building stock is challenging, particularly for existing and heritage buildings where conventional retrofit can be costly, disruptive or constrained by the building fabric. This project explores a complementary technology-led approach: using data, physical modelling and intelligent control to understand a building's dynamic energy performance and improve the efficiency and economics of low-carbon heating systems.
The project combines machine learning, physical modelling, data engineering and optimisation with a real-world deployment setting. An initial testbed is provided by buildings at Queens' College, Cambridge, where energy and heating data are being collected to better understand building performance and identify opportunities for practical intervention.
The successful candidate will work with heterogeneous sources of building data and help develop an integrated computational framework for modelling building dynamics, predicting energy demand and operating costs, and identifying and ultimately testing interventions that can improve efficiency. This will involve both research and prototype development, with an emphasis on methods that can ultimately be deployed and evaluated in real buildings.
Areas of work are expected to include a combination of:
- developing and maintaining unified datasets and data pipelines integrating building sensors, energy systems, weather and other relevant sources.
- analysing real-time and historical building-performance data and developing quantitative and economic measures against which interventions can be evaluated,
- developing predictive machine-learning models for quantities such as heating demand, electricity demand and operating costs, including their dependence on weather and building conditions,
- investigating machine-learning approaches, potentially including physics-informed models, reinforcement learning, and other methods for sequential decision-making and control,
- investigating interfaces with existing building-management and control systems.
An important feature of the project is that research will be carried out in dialogue with a real deployment environment. The successful candidate will therefore have considerable scope to help define and refine research questions, prototype new approaches, and respond to practical issues that arise from the data and buildings themselves.
Team and Environment
The successful candidate will work with Dr Challenger Mishra in the Department of Computer Science and Technology.
Experience in energy systems, building simulation, reinforcement learning, control, sensor data or physics-informed machine learning would be useful but is not required. We encourage applications from candidates who meet the expected qualifications even if they do not meet all of the desirable criteria.
Application
Applicants should upload a full curriculum vitae (CV) and a one-page covering letter outlining their relevant past experience, and include contact details for two referees.
Please note that applicants may be reviewed on a regular basis and may be invited to interview prior to the closing date. The University reserves the right to close the position early if a suitable appointment is made.
Click the 'Apply' button below to register an account with our recruitment system (if you have not already) and apply online.
Questions about the post and the recruitment process may be addressed to the HR Team at hr-admin@cst.cam.ac.uk
Please quote reference NR51196 on your application and in any correspondence about this vacancy.
The University actively supports equality, diversity and inclusion and encourages applications from all sections of society.
The University has a responsibility to ensure that all employees are eligible to live and work in the UK.
Download further information
Key information
Department/location
Department of Computer Science and Technology
Salary
£33,002-£35,608
Reference
NR51196
Category
Date published
28 September 2026
Closing date
13 October 2026