PhD Position in Justifications in Human-AI Teams for Hybrid Intelligence

Join our team for this fully funded four-year PhD project at Utrecht University! You will explore Justifications in Human-AI teams within the Hybrid Intelligence (HI) project. Hybrid Intelligence, funded by a ten-year Gravitation Grant by the Dutch Ministry of Education, Culture and Science, brings together many prominent AI researchers in the Netherlands. Our vision: to expand human intellect through ethical, explainable, and human-centered Human-AI teams collaborating to achieve common goals.

Your job
For Hybrid Intelligence (HI) teams to function effectively, all members–human and AI alike–must be able to exhibit behaviour that accounts for and is justifiable with respect to the shared team’s ethics and team norms. In this project, you will investigate computational models and mechanisms that enable AI agents in Hybrid Human-AI teams to learn, adapt, and utilise shared team norms through interactions to ensure their actions are aligned and justifiable. This includes exploring how and when AI can provide, or request, justifications for team members’ actions based on the team norms.

The project offers a unique opportunity to tackle questions such as:

• How can we computationally represent and learn evolving team norms in HI systems?
• How can we design AI agent architectures that integrate team norms into their decision-making processes to ensure that both AI and human behaviour is justifiable?
• What computational mechanisms enable the generation and requesting of justifications based on team norms and individual team member characteristics?
• How do AI-generated justifications impact trust and effectiveness within human-AI teams?

As a PhD candidate you will conduct research around the notion of justifiability, developing agent architectures for justified agency, and accounting for the dynamic and personalised nature of team interactions. You will contribute a novel methodology for designing responsible and explainable HI teams with justifiable AI behaviors, and metrics to assess the impact of justifications on team performance and trust. Finally, you will develop a framework for representing and reasoning about team norms and justifications, designing and evaluating algorithms for AI agents to learn, apply, and generate justifications in collaborative settings.

You will be co-supervised by Davide Dell’Anna (Utrecht University) and Myrthe Tielman (Delft University of Technology). As a PhD candidate your principal focus is on conducting scientific research, resulting in a PhD dissertation at the end of the project. Next to this you may be involved in teaching activities for 10-15% of your time, such as supporting the preparation and teaching of Bachelor's and Master's level courses, supervising student theses, managing research infrastructure and participating in public outreach. This position presents an excellent opportunity to develop an academic profile.

You have a technical Computer Science and Artificial Intelligence background (Msc), with expertise in one or more of the following areas:

• design and development of intelligent and social agents;
• understanding and modeling of norms, trust, and team dynamics in computational systems.
• Explainable AI and Social and Everyday explainability;
• application of Machine Learning (such as Reinforcement Learning), Symbolic AI techniques (such as formal systems), or NLP techniques, in Human-AI collaboration;
• Human-Computer Interaction and User Studies.

In addition to the required technical expertise, you have the following qualities:

• analytical and problem-solving skills;
• resilience and perseverance;
• intellectual curiosity and a proactive learning attitude;
• a genuine interest in collaboration.

We aim to create hybrid intelligence for everyone, see also our Diversity Statement. To do this, we need an inclusive and diverse team of researchers. We especially encourage people from underrepresented groups to apply for this job.

• a position for 18 months, with an extension to a total of four years upon successful assessment in the first 18 months;
• a gross monthly salary between €2,901 and €3,707 in the case of full-time employment (salary scale P under the Collective Labour Agreement for Dutch Universities (CAO NU));
• 8% holiday pay and 8.3% year-end bonus;
• a pension scheme, partially paid parental leave and flexible terms of employment based on the CAO NU.

In addition to the terms of employment laid down in the CAO NU, Utrecht University has a number of schemes and facilities of its own for employees. This includes schemes facilitating professional development, leave schemes and schemes for sports and cultural activities, as well as discounts on software and other IT products. We also offer access to additional employee benefits through our Terms of Employment Options Model. In this way, we encourage our employees to continue to invest in their growth. For more information, please visit Working at Utrecht University.

A better future for everyone. This ambition motivates our scientists in executing their leading research and inspiring teaching. At Utrecht University, the various disciplines collaborate intensively towards major strategic themes. Our focus is on Dynamics of Youth, Institutions for Open Societies, Life Sciences and Pathways to Sustainability. Sharing science, shaping tomorrow.

Working at the Faculty of Science means bringing together inspiring people across disciplines and with a variety of perspectives and backgrounds. The Faculty has six departments: Biology, Pharmaceutical Sciences, Information & Computing Sciences, Physics, Chemistry and Mathematics. Together, we work on excellent research and inspiring education. We do so, driven by curiosity and supported by outstanding infrastructure. Visit us on LinkedIn and discover how you can become part of our community.

The Department of Information and Computing Sciences (ICS) is nationally and internationally known for its research in computer science and information science. The department provides and contributes to the Bachelor's programmes in Computer Science, Information Science, and Artificial Intelligence and a number of research Master's programmes in these fields. It employs over 200 people, working in four divisions: Algorithms, AI & Data Science, Software and Interaction. The atmosphere is collegial and informal.

You will be part of the Responsible AI group, an international research group whose research focuses on designing and developing AI techniques, tools, and methodologies that enable computational systems to abide by legal, ethical, and social requirements while prioritising humans that will benefit from them.

As a member of the The Hybrid Intelligence Centre, you'll join a large group of PhD candidates and Postdocs working on related topics. On a daily basis you will join the several PhD candidates and Postdocs that are based at Utrecht University and in the Responsible AI group. The regular consortium meetings will offer you the opportunity to meet and connect with all the members and peers in the project.

For more information, please contact Davide Dell’Anna at d.dellanna@uu.nl.

Do you have a question about the application procedure? Please send an email to science.recruitment@uu.nl.