Eindhoven University of Technology is seeking applications for a postdoctoral research position in the NRO-funded project AI as a Social Agent to Support Group Learning Processes (CLARA). This innovative project explores the use of AI, particularly large language model (LLM)-based agents, as adaptive social agents to facilitate collaborative learning in Challenge-Based Learning (CBL) contexts.

The Role

You will be part of the Department of Industrial Engineering & Innovation Sciences (IE&IS) and play a key role within the CLARA consortium, collaborating with researchers from TU/e, the University of Twente, and Maastricht University. In partnership with a PhD candidate and the supervisory team, you will design, train, and iteratively improve the CLARA AI agent, merging advanced machine learning techniques with educational insights.

Responsibilities

• Develop and implement an NLP/LLM-based system to identify socio-cognitive and socio-emotional triggers in student interactions using the HASRL framework.
• Fine-tune large language models on educational datasets to ensure pedagogically valid and contextually appropriate agent responses.
• Collaborate with the PhD candidate and educational supervisors to create and assess adaptive scaffolding strategies delivered by the AI agent.
• Assist in pilot studies within real CBL classrooms, contributing to data collection and performance analysis.
• Conduct algorithmic fairness validation for the CLARA system, ensuring compliance with data governance and GDPR.
• Publish research findings in peer-reviewed journals and present at conferences.

Requirements

• PhD in Computer Science, Artificial Intelligence, or a related field.
• Expertise in large language models (LLMs), natural language processing (NLP), and machine learning, with a strong publication record.
• Proficiency in Python and ML frameworks (e.g., PyTorch, HuggingFace Transformers).
• Experience with model fine-tuning, prompt engineering, and agentic AI systems.
• Familiarity with responsible AI principles and supercomputing environments.
• Strong academic writing and communication skills in English.
• Ability to work effectively in an interdisciplinary team.

Nice to Have

• Experience in educational research or settings.
• Knowledge of multimodal data and time-series analysis.
• Interest in agentic AI systems and real-time inference.
• Awareness of Challenge-Based Learning frameworks.

What We Offer

• A postdoctoral position for 0.8 FTE (32 hours/week) for 2.5 years.
• Salary according to Dutch Universities Collective Labour Agreement, scale 10 (min. €4,241 max. €5,538 gross/month).
• Year-end bonus of 8.3% and annual vacation pay of 8%.
• High-quality training programs and mentoring from an interdisciplinary team.
• Opportunities for publication and participation in international conferences.
• Access to on-campus facilities including childcare and sports.
• Support for international candidates, including immigration assistance and tax compensation.

For more information about our employment conditions, please visit our website. If you recognize yourself in this profile and wish to learn more, please reach out to the hiring managers.

Application Process

To apply, please submit a complete application including a cover letter, CV, references, a representative publication or code portfolio, and a response to the technical challenge outlined in the job posting. Applications are due by 17 August 2026, with interviews scheduled for 14 September 2026. The expected start date is 1 November 2026.