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 the 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 Job

Project

Can we predict the outcomes of public policy, political elections, and other decisions? We are finding out by developing serious games 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/)). We are looking for an ambitious postdoctoral researcher who wants to be part of this initiative.

Responsibilities

You are the person who makes the simulations meaningful. The technical infrastructure produces results in the form of thousands of LLM-generated texts from prompts. Your job is to ensure that these results are grounded in real human behavior, real political dynamics, and real institutional logic. Specifically, this involves:

• Scenario Architecture. Each simulation is defined by a scenario with an initial world state, a set of agents, communication channels, institutional constraints, and document corpora. You will design scenarios focusing on negotiations regarding nature conservation policy and socio-ecological hybrid warfare.
• Construction of Agent Personas. For each agent, you define the identity prompt, the ideological vector, personality traits, decision model weights, and the affect parameters that control when agents escalate beyond their standard measure. This involves extracting positions, rhetorical styles, strategic preferences, and psychological profiles from real-world sources.
• Analysis and Validation of Simulation Results. After Monte Carlo runs, you analyze the outcome distribution (e.g., which policies emerge). You will also design validation of behavioral signatures (e.g., verifying that simulated agents exhibit the expected sentiment compared to empirical baselines).
• Publication and Dissemination. 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, a field with very few competitors and high visibility.

You will work closely with the Principal Investigator (Guillaume Chapron (https://www.slu.se/en/profilepages/c/guillaume-chapron/)) and a research engineer in AI (who is being recruited simultaneously). The three of you will form the core team.

Your Background

Requirements

• A PhD in Computational Social Science (or Political Science, Psychology, Behavioral Economics, Evolutionary Anthropology, or a related field) with strong quantitative skills. The PhD must be completed by the start date.
• Ability to reflect on strategic behavior, political dynamics, or social processes in a structured, analytical way, whether through formal models, experiments, or quantitative analysis.
• Willingness to work with AI and LLMs. You should be comfortable working critically with AI-generated results, interpreting how LLMs respond to instructions, and contributing to the design, testing, and refinement of prompts.
• Strong writing skills: clarity, precision, and the ability to communicate across disciplinary boundaries.

Merits

• Experience with agent-based modeling, game theory, simulation, or experimental methods in the social sciences.
• Experience with LLMs and their capacity to simulate human behavior, such as the emerging literature on "silicon subjects" and next-generation social simulations.
• Understanding of institutional design, legislative processes, or multi-level governance. The simulation maintains procedural constraints, and designing these correctly requires knowledge of how real institutions actually function.
• Reading proficiency in Swedish is not a requirement but an advantage.

Evaluation Criteria

Applications will be assessed based on the following:

• Intellectual depth and originality. We are looking for someone who has demonstrated the ability to produce genuinely new ideas, not just incremental extensions of existing work. Your doctoral thesis, publications, or research description should show that you think independently and are drawn to difficult, unexplored scientific problems.
• Interdisciplinary breadth. The ideal candidate is not easily captured by a single disciplinary label. If your work connects political behavior, psychology, strategic interaction, and computational methods, even in an unconventional way, you are more interesting to us than a narrow specialist with a longer publication list.
• Alignment with the project's ambition. This is a project aiming to be pioneering in a new field, and we want someone who finds this exciting rather than risky. Your application should clarify why this specific project, not just why a postdoc position. Since the research area is new, you must also be able to work in relative isolation.
• Interdisciplinary inclination. You will daily work with questions from very different disciplines: computer science, AI, ecology, political science, geopolitics. The ability to communicate across disciplinary boundaries 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 computational social science.

Employment Type:

Fixed-term employment for 24 months, with a possible extension.

Scope:

100 %.

Start Date:

By agreement, as soon as possible.

Application:

Apply via the button below no later than 2026-07-14. Information on what should be included in the application can be found at slu.se.