Research Associate in Large Language Models for Biodiversity Data Extraction (Fixed Term)

University of Cambridge; Cambridge; On-site; GBP 45,000 - 60,000; Full time

Job summary

University of Cambridge is seeking a Research Associate in the Department of Zoology to develop advanced LLM approaches for biodiversity forecasting within the CISGeMs framework. The role involves creating AI workflows to process millions of scientific papers, extract georeferenced species data, and integrate ecological, genomic, and climatic information for predictive modelling.

Collaboration spans ecology, genomics, and AI research groups.

Qualifications

• PhD in computer science, machine learning, artificial intelligence, bioinformatics, computational biology, or related discipline.
• Strong quantitative background with experience in LLMs, NLP, information extraction, retrieval-augmented generation or agentic AI systems.
• Excellent programming skills and experience with modern ML ecosystems and tools.

Responsibilities

• Develop agentic LLM-based systems to extract, organize and validate biodiversity information from literature.
• Design and implement AI workflows to process over one million papers for georeferenced biodiversity data.
• Collaborate with researchers across ecology, genomics and environmental data domains.
• Mentor junior researchers and contribute to shared software infrastructure and open-source tools.

Skills

AI workflow design

NLP / Information extraction

Programming in ML stacks

Interdisciplinary collaboration

Education

PhD in CS/ML/AI/bioinformatics

Tools

Python

PyTorch/TensorFlow

Job description

A Research Associate post is available in the Department of Zoology at the University of Cambridge to develop advanced large language model (LLM) approaches for biodiversity forecasting as part of a major research programme investigating how species and ecosystems respond to environmental change. The project aims to transform biodiversity prediction by integrating ecological, genomic, climatic, and environmental data within a unified modelling framework known as Climate-Informed Spatial Genomic Models (CISGeMs). These models provide a powerful mechanism for reconstructing population histories and forecasting future biodiversity trajectories, creating new opportunities to understand and predict biological responses to climate change at unprecedented spatial and temporal scales.

The principal aim of this post is the development of agentic LLM-based systems that can extract, organise, and validate biodiversity information from the published scientific literature at unprecedented scale. The successful candidate will design and implement AI workflows capable of processing more than one million scientific papers to identify and extract georeferenced information on species distributions, ecological interactions, demographic processes, environmental associations, and other biodiversity-relevant data. These data will form a key component of the CISGeM framework, complementing genomic, climatic, and environmental datasets and enabling a richer representation of biodiversity dynamics through space and time. The researcher will contribute directly to the development of a new generation of biodiversity forecasting models that combine mechanistic understanding with state-of-the-art artificial intelligence.

The successful candidate will join a large and highly interdisciplinary research group comprising more than 20 PhD students and postdoctoral researchers working across ecology, evolution, conservation, and genomics. They will work closely with researchers developing deep learning approaches for population genomic inference, population geneticists generating large genomic datasets, and ecological modellers applying the resulting tools to questions in biodiversity conservation. The role will also involve substantial collaboration with other projects across the University of Cambridge focused on large-scale knowledge extraction and retrieval from the scientific literature, providing opportunities to contribute to the development of next-generation AI methods for scientific discovery.

Candidates should have a PhD in computer science, machine learning, artificial intelligence, bioinformatics, computational biology, or a related discipline. A strong quantitative background and substantial experience working with large language models, natural language processing, information extraction, retrieval-augmented generation, or agentic AI systems are essential. Excellent programming skills and experience with modern machine learning ecosystems and tools are expected. Experience in ecology, biodiversity science, geospatial analysis, or scientific text mining would be advantageous but is not essential.

The successful applicant will be expected to contribute actively to the intellectual life of the group. This includes participating in weekly hackathons and collaborative coding sessions, contributing to the development of shared software infrastructure and open-source tools, mentoring junior researchers where appropriate, and sharing expertise in large language models and artificial intelligence across the programme. The position provides an outstanding opportunity to work at the forefront of AI-driven environmental science and to help establish new approaches for transforming the scientific literature into actionable biodiversity knowledge at global scale.

Interviews are planned for the week commencing Monday, 31 August 2026.

Fixed-term: The funds for this post are available for up to 3 years.

Flexible working requests will be considered. Due to the nature of this role, it is based entirely on site.

Informal enquiries are welcomed and should be directed to: Prof Andrea Manica [email: [e-mail]]

If you have any queries regarding the application process, please contact Zoology HR Office [email: [e-mail]]

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.