You will investigate how Vision-Language Models (VLMs) can be adapted through techniques like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO). These approaches will allow the models to learn from interactions with cultural heritage experts, progressively improving their ability to address questions about representation. The project specifically focuses on developing systems that can adapt to individual users rather than assuming a universal perspective on bias.
The research will make methodological contributions in three converging directions: bias mitigation in AI systems, personalization to individual users, and interactive learning. While existing research typically addresses these areas separately, your work will explore their intersection specifically for visual cultural heritage analysis. This approach has the potential to create tools that respect the subjective nature of bias analysis while still providing meaningful automated assistance.
Your evaluation approach will combine technical benchmarks with user studies involving real cultural heritage experts and students. This dual methodology ensures your systems not only perform well on standard measures but also genuinely help users understand representation issues in collections. Throughout the project, we will work with cultural institutions and experts to develop ethical guidelines for this sensitive research area, ensuring your technical innovations have real impact in the cultural heritage sector.

As the PhD candidate on this project within the Hybrid Intelligene Centre, you will be expected to contribute to the project, described above, and:

• pursue and complete a PhD thesis within the appointment duration of four years;
• collaborate with researchers in the lab and the Hybrid Intelligence Centre;
• present intermediate research results at conferences and workshops, and publishing in proceedings and journals;
• assist in teaching activities.

For this position you will be supervised by Dr. Nanne van Noord (University of Amsterdam) and Dr. Shenghui Wang (University of Twente).

• A Master’s degree in a relevant disciplines, such as AI, computer vision, human-computer interaction, or a closely related field;
• technical skills and scientific interest to conduct cutting-edge interdisciplinary research in artificial intelligence and cultural heritage;
• ability to work with a high degree of independence and eagerness to contribute your own ideas;
• good writing and presentation skills;
• full proficiency in spoken and written English.

Experience with or an interest in cultural heritage, bias, and human-centred research are considered a plus. We strongly encourage applications coming from a unique perspective. Tell us how your background fits within the project.

A temporary contract for 38 hours per week for the duration of 4 years (the initial contract will be for a period of 18 months and after satisfactory evaluation it will be extended for a total duration of 4 years). The required starting date is within 2025. This should lead to a dissertation (PhD thesis). We will draft an educational plan that includes attendance of courses and (international) meetings. We also expect you to assist in teaching undergraduates and master students.

The gross monthly salary, based on 38 hours per week and dependent on relevant experience, ranges between € 2,901 to € 3,707 (scale P). This does not include 8% holiday allowance and 8,3% year-end allowance. The UFO profile PhD candidate is applicable. A favourable tax agreement, the ‘30% ruling’, may apply to non-Dutch applicants. The Collective Labour Agreement of Universities of the Netherlands is applicable.

Besides the salary and a vibrant and challenging environment at Science Park we offer you multiple fringe benefits:

• 232 holiday hours per year (based on fulltime) and extra holidays between Christmas and 1 January;
• multiple courses to follow from our Teaching and Learning Centre;
• a complete educational program for PhD students;
• multiple courses on topics such as leadership for academic staff;
• multiple courses on topics such as time management, handling stress and an online learning platform with 100+ different courses;
• 7 weeks birth leave (partner leave) with 100% salary;
• partly paid parental leave;
• the possibility to set up a workplace at home;
• a pension at ABP for which UvA pays two third part of the contribution;
• the possibility to follow courses to learn Dutch;
• help with housing for a studio or small apartment when you’re moving from abroad.

Are you curious to read more about our extensive package of secondary employment benefits, take a look here.