Postdoc Explainable Human Behavior and Affective Predictions

Help develop explainable AI to support human-AI interactions. As a Postdoctoral Researcher at TU Delft, you will investigate how multimodal AI can understand, explain and communicate predictions about human behaviour, contributing to trustworthy intelligent systems for high-impact applications.

Job description

Human behavior understanding is becoming an essential component across a range of application areas, including education and healthcare. As these systems are increasingly deployed in high-stakes environments, there is a growing need for machine learning models that are not only accurate but also transparent and explainable. This project focuses on the automatic perception of situational interest and state epistemic curiosity, which are motivational factors that influence human interaction and  learning. While multimodal systems are already being developed to monitor physical and cognitive engagement, current approaches offer limited interpretability and often do not provide meaningful explanations of their predictions to downstream users.

A central aim of this project is to investigate how Vision-Language Models (VLMs), Multimodal Large Language Models (MLLMs), and related technologies can support explanation in situated conversational settings. We view explanation not as a static output, but as an interactive process that evolves through human-human and human-AI dialogue, where meaning emerges through grounding, clarification and feedback. A possible application domain for this research is augmented and mixed reality environments, which require real-time perception and explanation within dynamic contexts. Possible research directions include mechanistic interpretability of multimodal models, concept-based explanations grounded in affect and behaviour theory, and multimodal sensing using vision, audio and physiological signals. The project will also focus on developing interactive systems that support real-time dialogue and user questioning, with deployment in immersive environments.

You will be embedded within the Interactive Intelligence Group in the Department of Intelligent Systems at the Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS). More information about the faculty can be found at the EEMCS Faculty website and about the department at the Department of Intelligent Systems website. The research environment is open and collaborative, and participation in group activities is highly encouraged. Importantly, you will also participate in the Hybrid Intelligence Centre, a Dutch consortium dedicated to developing and researching Hybrid Intelligence. Consortium meetings and occasional visits to collaboration partners are part of the project. We embrace an inclusive culture where you can benefit from tailored mentorship and training to support your professional growth.

Job requirements 

• You hold, or expect to obtain before the start of the project, a PhD degree in a relevant discipline.
• You have a relevant research track record in one or more of the following areas: (1) Generative AI and machine learning, (2) affective computing, (3) human-computer interaction or collaborative AI, and (4) interaction design, experimental design or evaluation of collaborative systems.
• You have a strong interest in interdisciplinary research at the intersection of AI, human behaviour understanding and interactive intelligent systems.
• You have excellent communication skills and a proactive attitude.
• You are able to work effectively in a multidisciplinary team.

Conditions of employment 

• Duration of contract is 3 years. Temporary. This is a three-year position, consisting of an initial one-year contract with a two-year extension subject to good performance.
• A job of 38-40 hours per week. 
• Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities.
• An excellent pension scheme via the ABP. 
• The possibility to compile an individual employment package every year. 
• Discount with health insurers on supplemental packages. 
• Flexible working week. 
• Every year, 232 leave hours (at 38 hours). You can also sell or buy additional leave hours via the individual choice budget. 
• Plenty of opportunities for education, training and courses. 
• Partially paid parental leave 
• Attention for working healthy and energetically with the vitality program. 

Will you need to relocate to the Netherlands for this job? TU Delft is committed to make your move as smooth as possible! The HR unit, Coming to Delft Service, offers information on their website to help you prepare your relocation. In addition, Coming to Delft Service organises events to help you settle in the Netherlands, and expand your (social) network in Delft. A Dual Career Programme is available, to support your accompanying partner with their job search in the Netherlands.  . 

Additional information
If you would like more information about this vacancy or the selection procedure, please contact Stephanie Tan, via S.Tan-1@tudelft.nl.

Application procedure
Are you interested in this vacancy? Please apply no later than 9 October 2026 via the application button and upload the following documents:

• CV
• Motivational letter

You can address your application to Stephanie Tan. Applications are reviewed on a rolling basis until the vacancy closes.

Please note:

• You can apply online. We will not process applications sent by email and/or post. 
• As part of knowledge security, TU Delft conducts a risk assessment during the recruitment of personnel. We do this, among other things, to prevent the unwanted transfer of sensitive knowledge and technology. The assessment is based on information provided by the candidates themselves, such as their motivation letter and CV, and takes place at the final stages of the selection process. When the outcome of the assessment is negative, the candidate will be informed. The processing of personal data in the context of the risk assessment is carried out on the legal basis of the GDPR: performing a public task in the public interest. You can find more information about this assessment on our website about knowledge security.
• Please do not contact us for unsolicited services.