Student assistant (f/m/x) - Leveraging large-language models for agent-based model synthesis, development, and documentation

Student assistant (f/m/x) - Leveraging large-language models for agent-based model synthesis, development, and documentation

The job

Agent-based models (ABMs) are powerful tools for exploring complex socio-environmental systems. However, developing ABMs is often time-consuming and requires substantial expertise.
Recent advances in generative AI, particularly large language models (LLMs), offer promising opportunities to support the ABM modelling process—by facilitating model synthesis, code generation, and documentation.
Our research project explores how LLMs can support these different steps of the ABM development cycle and we are searching for a highly motivated student assistant to support us. The insights gained will help future modelers to use LLMs more effectively, improving both the efficiency and transparency of ABM workflows.

Place of work

Leipzig, mobile working partially possible

Working time

12.5% - 25% (5-10h/week)

Contract limitations

limited contract / 3 months

Contact

Your contact for any questions you may have about the job:
Julia Kunkel (julia.kunkel@ufz.de)
Christian Klassert (christian.klassert@ufz.de)

Your application

Please submit your application via our online portal with your cover letter, CV (please omit your photo, age, or marital status) and relevant attachments.

Diversity and Inclusion

The UFZ has a strong commitment to diversity and actively supports equal opportunities for all employees regardless of their origin, religion, ideology, disability, age or sexual identity.
We look forward to applications from people who are open-minded and enjoy working in diverse teams.

The UFZ

The Helmholtz Centre for Environmental Research (UFZ) with its 1,100 employees has gained an excellent reputation as an international competence centre for environmental sciences. We are part of the largest scientific organisation in Germany, the Helmholtz association. Our mission: Our research seeks to find a balance between social development and the long-term protection of our natural resources.

The job

Agent-based models (ABMs) are powerful tools for exploring complex socio-environmental systems. However, developing ABMs is often time-consuming and requires substantial expertise.
Recent advances in generative AI, particularly large language models (LLMs), offer promising opportunities to support the ABM modelling process—by facilitating model synthesis, code generation, and documentation.
Our research project explores how LLMs can support these different steps of the ABM development cycle and we are searching for a highly motivated student assistant to support us. The insights gained will help future modelers to use LLMs more effectively, improving both the efficiency and transparency of ABM workflows.

Your tasks

• Prompt Design and evaluation: Assist in developing effective prompts and evaluation criteria for three steps in the agent-based modelling cycle.

The prompts should then be systematically applied to evaluate LLMs in supporting the following three tasks in the ABM process using API code:

• Model documentation: Test the ability of LLMs to document ABM code in standard protocol formats, e.g., the "Overview, Design concepts, and Details" (ODD) protocol
• Code generation: Test the ability of LLMs to generate ABM code (e.g. in NetLogo or Python) from model descriptions or protocols
• Model extensions: Test the ability of LLMs to synthesize existing ABMs with the aim to identify potential research gaps and model extensions 

We offer

• Excellent supervision that supports your personal and professional development
• Exciting insights into the work of a leading research institute
• The chance to work in interdisciplinary, international teams and benefit from a wide range of perspectives
• The opportunity to contribute and actively shape your own ideas and impulses
  right from the start
• Modern technical equipment and IT service to optimally support your work

Your profile

• You are enrolled in a study program such as computer science, data science, cognitive science, computational social/environmental science, or a related field with a strong interest in programming and AI-based tools
• Experience or strong interest in prompt engineering and working with LLMs
• Experience in agent-based modelling and/or socio-environmental systems is a plus
• High level of motivation, independence, and reliability

Apply now

Application deadline: 10.08.2025

More information about jobs at the UFZ:
www.ufz.de/career

LinkedIn @UFZ

Family Support

International Office

Accessibility

Diversity, Equity & Inclusion

» back