Research Associate in AI-Enabled Hydrological Modelling and Data Assimilation

Location: South Kensington Campus, London

About the role:

Are you interested in shaping the future of global water modelling using AI?

The Research Associate in AI-Enabled Hydrological Modelling and Data Assimilation will develop innovative methods that combine large language models, data assimilation, and local knowledge to improve global water reanalysis. Working within an international, interdisciplinary team, the role contributes to cutting-edge research with real-world impact on water security and decision-making.

What you would be doing:

You will conduct cutting-edge research at the intersection of hydrology, data assimilation, and artificial intelligence, with a particular focus on integrating large language models and diverse knowledge sources into global water reanalysis systems. These systems provide comprehensive, retrospective reconstructions of the state of freshwater systems and are critical for understanding water availability and informing local and global decision-making. Your work will involve developing, testing, and applying novel computational methods to combine quantitative data with qualitative and semi-quantitative information, such as local expert knowledge and citizen science observations, to improve the robustness, actionability, and local relevance of water reanalysis products.

You will work closely with an international, interdisciplinary consortium, collaborating with researchers across environmental science, data science, and social science, and contributing to high-quality publications, open-source software, and project deliverables. You will also support the supervision of students and early career researchers, contribute to research funding proposals, and present your findings at internal meetings and international conferences.

What we are looking for:

We are looking for a motivated and collaborative researcher who brings a strong technical foundation alongside curiosity and initiative. In particular, you will have:

• Experience conducting computational or data-driven research, ideally in environmental, earth system, or related domains
• Skills in data analysis, statistical modelling, machine learning, or data assimilation, with an interest in large language models and emerging AI methods
• The ability to work independently and collaboratively within an interdisciplinary and international research team

This role would suit someone who enjoys tackling complex methodological challenges and contributing to research with global relevance and real-world impact.

What we can offer you:

• The opportunity to work on a high-profile, internationally funded research programme at the forefront of AI, data assimilation, and global water security
• The chance to collaborate with a world-leading international consortium, including academic, policy, and practitioner partners across multiple continents
• Support to develop an independent research profile, including opportunities to publish in high-impact journals, contribute to grant applications, and present at international conferences
• Access to excellent computational resources, training, and professional development offered by Imperial College London
• Opportunities to supervise and mentor PhD students, MSc projects, and early career researchers
• A supportive and inclusive working environment that values open science, responsible AI, and real-world impact
• Being a member of the Data Learning and AI for Good group at Imperial, providing access to a vibrant, interdisciplinary research environment and a strong community of AI and data science researchers

Further Information

This is a full-time post (35 hours per week).

This role is for a fixed-term contract for 24 months. (with possibility of extension).

If you require any further details about the role, please contact: Rossella Arcucci - r.arcucci@imperial.ac.uk

To apply, please visit Jobs | Imperial College London and search for reference number: ENG03795

Closing Date: 4^th March 2026

Advert information