Research Fellow in Geo-LLMs

University of Leeds - School of Computer Science

Location:	Leeds
Salary:	£41,064 to £48,822 per annum
Hours:	Full Time
Contract Type:	Fixed-Term/Contract

Placed On:	13th February 2026
Closes:	25th February 2026
Job Ref:	EPSCP1180

Do you want to further your career in one of the UK’s leading research intensive universities? Are you passionate about developing the fundamentals of AI in the context of applications to Geographical Information Science? Are you already skilled in the use and evaluation of (multimodal) Large Language Models (MLLMs)?

Recent Artificial Intelligence (AI) research has given rise to a paradigm shift brought by Large Language Models (LLMs). Though LLMs arose from research in Natural Language Processing (NLP), it is well-known today that zero-shot and few-shot transfer learning methodologies as well as novel prompting strategies make their deployment possible beyond the NLP field, achieving impressive performance on a significant range of domains and downstream tasks. However, the deployment of LLMs in geographic information systems is still in its infancy. The Chist-ERA Geo-R2LLM project aims to create a novel paradigm for building knowledgeable and multimodal geographic LLMs by rethinking LLMs generation mode with retrieval and reasoning over multiple multimodal external knowledge sources to ground predictions. The improved multimodal geographic LLMs will be integrated in a geospatio-temporal AI (GeoAI) system prototype and evaluated on a pilot application related to context-aware navigation systems in a complex urban environment. Navigation services can be considered as one of the most critical and widely adopted location-based services in modern society, hence the project has potentially strong impact also outside of academia. This research will lead to fundamental advances in multiple disciplines spanning GeoAI, spatio-temporal reasoning, information retrieval, and natural language understanding, laying the groundwork for more effective AI platforms for various domains that relate to geography and geographical information science.

The Geo-R2LLM project consists of the University of Toulouse 3, UT3-IRIT (France) (coordinator), Aalto University (Finland), the University of the Basque Country (Spain), the University of Leeds and Ghent University (Belgium).

What we offer in return

• 26 days holiday plus approx.16 Bank Holidays/days that the University is closed by custom (including Christmas) – That’s 42 days a year!
• Generous pension scheme options plus life assurance
• Health and Wellbeing: Discounted staff membership options at The Edge, our state-of-the-art Campus gym, with a pool, sauna, climbing wall, cycle circuit, and sports halls.
• Personal Development: Access to courses run by our Organisational Development & Professional Learning team.
• Access to on-site childcare, shopping discounts and travel schemes are also available.

And much more!

To explore the post further or for any queries you may have, please contact:

Prof Anthony (Tony) Cohn
Tel: +44 (0)113 343 5482
Email: a.g.cohn@leeds.ac.uk