Research Engineer in AI-driven Social Simulations (application deadline 31/07/2026)

Description du poste

Can we foresee the outcomes of public policies, political choices 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 policies, and hybrid-threat scenarios) in which every actor is an autonomous AI agent powered by Large Language Models (LLMs). These agents simulate real-world stakeholders, from government ministers to interest groups, and interact through natural language in complex strategic settings. We then run thousands of iterations to map the distribution of outcomes.

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

Our goal is to build a novel methodology at the intersection of AI, ecology, political science, and complex system analysis that may change how policies are designed and stress-tested and how governments prepare for crises. We are looking for ambitious research engineer to join this effort.

Tasks and duties

You will be the person who makes the simulations actually run. Concretely, this means:

Building the LLM-agent infrastructure (from an existing working implementation). Each agent has a multi-tier memory and an affect state that modifies both prompts and available actions, and a strategic reasoning layer that tracks reputation, commitments, and mental models of other agents.
Extending and maintaining the multi-agent simulation framework. A simulation runs dozens of concurrent LLM instances, communicating through structured message-passing protocols. You will develop and maintain this framework, including the validation methodology.
Running large-scale Monte Carlo simulations at scale on GPU-enabled HPC clusters (e.g. NAISS).
Publishing and dissemination of the project results. You will co-author scientific publications from the project. The research will produce papers 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/) and a postdoctoral researcher in computational social science (to be recruited concurrently). The three of you will form the core team.

Profil recherché

Required
A degree in computer science, engineering, physics, applied mathematics, or a related quantitative field. A Master or 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 incorporate cutting-edge generative AI developments into the project.
Experience with software engineering 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.
Desirable
Experience with LLMs, including programmatic use through APIs and local deployment. The candidate should be able to select, configure, adapt, and critically evaluate LLMs for research applications.
Experience with deep reinforcement learning, agent-based modelling, 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 submission, GPU workflows, and managing 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.
Assessment criteria
Applications will be assessed on the following:

Demonstrated technical ability. We care more about what you have built, than about what courses you have taken. A GitHub portfolio, a deployed system, a well-documented side project, or a track record of solving hard AI problems will carry more weight than a list of credentials.
Autonomy and resourcefulness. This is a small team doing frontier work, so the role requires someone who can diagnose problems independently, make pragmatic technical decisions, and keep complex systems running. If that excites rather than worries you, this is the right position.
Collaborative disposition. You will work daily with questions from very different disciplines: ecology, political science, geopolitics. The ability to communicate technical constraints and possibilities to non-technical collaborators is essential. Interpersonal skills will form an important part of the assessment.