Post-Doctoral Research Associate in AI-enabled causal evaluation of nature

Smith School of Enterprise and the Environment, School of Geography and the Environment This is an exciting opportunity to join the new Sustainability & AI Research Hub at the Smith School of Enterprise and the Environment. Our flagship project addresses a fundamental problem in nature conservation: despite annual investments exceeding $100 billion, global biodiversity continues to decline, in large part because decision-makers lack credible causal evidence about what actually works, and why. The project proposes to develop an AI enabled causal inference platform for nature conservation and land-use policy, which will streamline the currently fragmented process of identifying impact across individual case studies. Responsibilities

• Manage own academic research and administrative activities. This involves small-scale project management to coordinate multiple aspects of work to meet deadlines
• Research and apply advanced machine learning and causal methods, so they can be applied to understand the impact of interventions in complex social-ecological contexts
• Design and implement a modular software architecture for the causal inference platform, integrating and adapting existing estimators and libraries
• Generate realistic simulated datasets replicating conservation intervention scenarios, and use these to systematically test and validate the platform
• Develop a basic visualisation dashboard to allow end users to interact with and interpret estimation results
• Collaborate in the preparation of research publications and book chapters
• Analyse additional data provided by team members to further test the platform, reviewing and refining theories as appropriate
To be a successful candidate;
• , Grade 7 Hold, a PhD/DPhil in Statistics, Computational Statistics, Economics, Quantitative Environmental Science, or a closely related quantitative discipline (e.g. Computer Science, Data Science), with a research focus on causal inference, statistical modelling, &/or machine learning methods
• Or underfill at Grade 6, be close to completion of a PhD/DPhil in Statistics, Computational Statistics, Economics, Quantitative Environmental Science, or a closely related quantitative
  
  discipline (e.g. Computer Science, Data Science) for candidates with potential but less experience who are seeking a development opportunity, for which an initial appointment with the responsibilities adjusted accordingly, Strong grounding in causal inference methods
• Experience with machine learning methods, particularly where integrated with causal or statistical reasoning
• Demonstrable proficiency in Python
• Good software engineering skills: modular design, version, reproducible pipelines, systematic testing
• Ability to design and generate synthetic datasets with specified statistical or causal properties
• Ability to work independently from PI, provided methodological specifications, managing own time and deliverables effectively
• Excellent written skills, including the ability to document methods and code clearly for research audiences
• A commitment to demonstrating respect, courtesy and consideration in interactions with members of the University community.
You must have the Right to Work within the UK, as this position may not amount to enough points under the points-based immigration system in the UK.

Enquiries may be directed to recruit@ouce.ox.ac.uk
• . The closing date for applications is midday on 18 May 2026. Interviews date TBC
We offer very generous benefits, some of which are:
• Generous holiday allowance of 38 days, including bank holidays
• Hybrid working
• Membership of the Oxford staff pension scheme
• Discounted bus travel
• Cycle loan scheme
• Plus, many other University benefits