Postdoc Researcher in Hybrid AI Sensemaking

This postdoctoral position focuses on Hybrid AI Sensemaking: developing hybrid intelligent systems in which AI tools support and learn from people interacting to make sense of something. That “something” can relate to, for example, group decision-making, solving a problem, doing research together, understanding each other better, and negotiation. Sense-making is a part of all these processes: what are they talking about, what do they want, need, and value? What are they concerned about? What AI techniques and intelligent agents can we develop to work supportively and/or unobtrusively along with them to discover alignments, and discover and bridge gaps?

This project will focus on group sensemaking through collaborating with AI agents. We take a human-centered approach. We will deploy Research through Design to design these agents and AI techniques to analyze text entries (and text entries obtained from the audio) obtained from human-agent and human-human interactions to construct the domain models and participant perspectives (which include their preference profiles). Generative AI will be used for various functions, e.g., to provide perspective-based summaries and to propose ideas to close the gap between perspectives.

A central challenge of this project lies in the design of interaction processes that effectively integrate AI into both human-human and human-AI collaborations. This includes developing mechanisms for when and how AI agents should intervene, how they represent and communicate data, and how they adapt to evolving group dynamics over time. A specific interest is group decision-making and sensemaking through co-creation processes. This introduces technical challenges in modeling how ideas emerge and evolve. AI agents should synthesize information through co-creation sessions by suggesting alternatives, reframing problems, or combining perspectives. Therefore, this project also involves designing collaborative protocols and experimentally validating such protocols. Insights could contribute to a general recipe of human-AI hybrid interactions where we ensure that human participants remain meaningfully engaged and retain oversight in sensemaking. Addressing these challenges requires combining advances in multimodal modeling, interaction design, and adaptive systems.

Job requirements

We are looking for applicants who have or expect to receive a PhD degree before joining the project. Applications have a relevant track record in one or more of the following fields:

1. human-computer interaction, collaborative AI
2. Generative AI/machine learning
3. interaction design, experimental design, or evaluation of collaborative systems
4. group decision-making and co-creation

Conditions of employment

• Duration of contract is 3 years (Temporary).
• 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.