Vacant job

Department of Ecology

Swedish University of Agricultural Sciences (SLU) is one of Northern Europe's largest academic environments for ecological research, offering a dynamic and excellent research environment with modern infrastructure. The Department of Ecology has approximately 150 employees, of whom around 40 work at the Grimsö Research Station in Bergslagen. Together, SLU's Ecological Centre and Grimsö Research Station conduct research on sustainable agriculture and forestry, plant protection, nature conservation, and wildlife management, contributing scientific knowledge to support environmental policy in Sweden and Europe.

About the Position

Project

Can we predict the outcomes of public policy, political elections, and other decisions? We are finding out by developing wargames and running them using AI.

We are building large-scale simulations of societal processes (environmental negotiations, nature conservation policy, and hybrid threat scenarios) where each actor is an autonomous AI agent driven by large language models (LLMs). These agents simulate real stakeholders, from government ministers to interest groups, and interact through natural language in complex strategic situations. We then run thousands of iterations to map the distribution of outcomes.

This initiative is part of the new research program Articulating Complexity (https://www.slu.se/articulating-complexity/ (https://www.slu.se/articulating-complexity/)), hosted at the Swedish University of Agricultural Sciences (SLU) and led by Guillaume Chapron (Associate Professor). It is funded by grants from the Swedish Research Council (VR), the Mistra Foundation for Environmental Strategy Research, and the Swedish Research Council for Sustainable Development (FORMAS).

Our goal is to build a new methodology at the intersection of AI, ecology, political science, and complex systems analysis that can change how policy is designed, stress-tested, and how governments prepare for crises. We are seeking an ambitious research engineer who wants to be part of this initiative.

Responsibilities

You are the person who makes the simulations actually work. Specifically, this entails:

• Building the LLM agent infrastructure (based on an existing working implementation). Each agent has a multi-layered memory and an affective state that modifies both prompts and available actions, as well as a strategic reasoning layer that tracks reputation, commitments, and mental models of other agents.
• Further developing and maintaining the multi-agent-based simulation framework. A simulation runs dozens of concurrent LLM instances that communicate through structured message protocols. You will develop and maintain this framework, including validation methodologies.
• Running large-scale Monte Carlo simulations on GPU-enabled HPC clusters (e.g., NAISS).
• Publication and dissemination of the project's results. You will co-author scientific publications from the project. The research will produce articles at the intersection of computational social science, ecology, security studies, and AI.

You will work closely with the PI (Guillaume Chapron https://www.slu.se/en/profilepages/c/guillaume-chapron/ (https://www.slu.se/en/profilepages/c/guillaume-chapron/)) and a postdoc in computational social science (who is being recruited simultaneously). The three of you will form the core team.

Your Background

Requirements

• A degree in computer science, engineering, physics, applied mathematics, or a related quantitative field. A master's or civil engineering degree is sufficient; a PhD is welcome but not required.
• Strong programming skills, especially in Python, and sufficient understanding of machine learning/deep learning to work effectively with modern generative AI systems. Ability to assess and integrate cutting-edge generative AI developments into the project.
• Experience with software development practices such as version control, testing, documentation, modular design, and reproducible workflows.
• Ability to work independently, debug complex systems under time pressure, and take ownership of technical infrastructure.

Merits

• Experience with LLMs, including programmatic use via APIs and local deployment. The candidate should be able to select, configure, customize, and critically evaluate LLMs for research applications.
• Experience in deep reinforcement learning, agent-based modeling, or multi-agent systems, including the design of simulation environments, interacting agents, decision rules, feedback mechanisms, and scenario-based analyses.
• Experience with high-performance computing: batch job management, GPU workflows, and handling large-scale computational experiments.
• Interest in the application domain: nature conservation, environmental policy, political science, geopolitics, and security studies, complex adaptive systems. You do not need a formal background in these fields, but you should find them interesting.

Evaluation Criteria

Applications will be assessed based on the following:

• Demonstrated technical ability. We care more about what you have built than which courses you have taken. A GitHub portfolio, a deployed system, a well-documented side project, or merits from solving difficult AI problems weigh heavier than a list of qualifications.
• Independence and ingenuity. This is a small team conducting cutting-edge research, and the role requires someone who can diagnose problems independently, make pragmatic technical decisions, and keep complex systems running. If this appeals to you rather than worries you, this is the right position.
• Collaboration skills. You will daily work with questions from very different disciplines: ecology, political science, geopolitics. The ability to communicate technical limitations and opportunities to non-technical partners is essential. Interpersonal skills will form an important part of the assessment.

Location:

The position is located either at Grimsö or in Uppsala, with the possibility of being partially based at another Swedish academic institution with core competence in AI and machine learning.

Employment Type:

Fixed-term employment for 12 months with a possible extension.

Scope:

100 %.

Start Date:

By agreement, as soon as possible after recruitment.

Application:

The application should include (1) a cover letter explaining why you are applying for the position (max 3 pages), (2) a CV including a full publication list if applicable, (3) copies of degree certificates, (4) a copy of a passport if the applicant is not a Swedish citizen, (5) a list of at least two reference persons and their contact details, and (6) any work that the candidate considers relevant for the position.

We welcome your application via the button below by 2026-07-14.