Research Fellow in Causal Inference and Ecology

Ecology Jobs; Southampton; On-site; GBP 42,000 - 62,000; Full time

Job summary

University of Southampton invites applications for a Research Fellow to join the PRECISE project. You will develop and evaluate causal-inference methods, work with large observational datasets and publish reproducible workflows.

Based in the School of Geography and Environmental Science, you will collaborate with partners including UKCEH and NINA. The expected start date is 1 February 2027, with a focus on methodological development and study design.

Qualifications

• Hold a PhD or equivalent in a relevant quantitative field.
• Strong causal-inference and quantitative expertise.
• Experience analysing observational data and ecological questions.
• Ability to develop reproducible, open-source software and workflows.
• Excellent communication and collaboration across teams.

Responsibilities

• Develop and evaluate causal-inference methods for ecology.
• Analyse benchmark and observational data with reproducible workflows.
• Create tutorials and guidance for best-practice analyses.
• Collaborate with partners at Southampton, UKCEH and NINA.

Skills

Quantitative modelling

R/Python analysis

Causal inference

Reproducible research

Publications/outputs

Collaboration

Education

PhD or equivalent in quantitative discipline

Tools

R

Python

Git/high-performance computing

Job description

Overview

We have an exciting opportunity for a Research Fellow to join the UKRI-funded PRECISE (Precision Ecology for a Changing World) project. You will help establish Precision Ecology, which seeks to predict the effects of conservation interventions in specific ecological contexts. Moving beyond average effects, the project will predict site-specific responses to environmental management and restoration, supporting effective conservation decisions.

Overview

We have an exciting opportunity for a Research Fellow to join the UKRI-funded PRECISE (Precision Ecology for a Changing World) project. You will help establish Precision Ecology, which seeks to predict the effects of conservation interventions in specific ecological contexts. Moving beyond average effects, the project will predict site-specific responses to environmental management and restoration, supporting effective conservation decisions.

Based in the School of Geography and Environmental Science at the University of Southampton, you will work with researchers at Southampton, the UK Centre for Ecology & Hydrology (UKCEH) and the Norwegian Institute for Nature Research (NINA), and international collaborators in statistics, causal inference and ecological modelling.

You will play a leading role in developing and evaluating methods for causal inference and causal prediction in ecology. Using benchmark datasets produced through ecological simulations and large observational datasets assembled by project partners, you will investigate how sampling strategies and data characteristics affect the performance of alternative causal-inference and machine-learning workflows. You will identify which approaches perform best under different conditions and translate the findings into practical guidance.

You will create reproducible, open-source software, analytical workflows, tutorials and guidance. With project partners, you will develop best-practice frameworks for analysing observational datasets and designing ecological studies and monitoring programmes. The role focuses on methodological development, study design and causal prediction, rather than ecological simulation modelling.

You should hold a PhD, or have equivalent professional experience, in a relevant quantitative discipline. We welcome applicants with strong causal-inference and quantitative expertise who want to apply these approaches to ecological questions. Ecological experience is desirable but not essential, provided you are willing to develop relevant ecological and spatial knowledge.

You Should Have

• Strong quantitative-modelling skills and experience analysing complex observational data.
• Programming and data-analysis experience using R, Python or related software, including reproducible, well-documented workflows.
• Understanding of causal inference and its application to observational data.
• Understanding of reproducible research and Open Science principles.
• Evidence of independent research and communication through publications, software, reports or equivalent outputs.
• Excellent organisational, communication and collaborative skills.

Experience in applying causal inference methods, machine learning, geospatial or ecological analysis, or high-performance computing would be advantageous.

For further information, contact Dr Becks Spake at [e-mail].

The expected start date of this role is 1st February 2027.