PhD Position in Learning Graphical Models for Risk-Based Inspection

Join our exciting research project as PhD candidate at Utrecht University and become part of the research collaboration AI4Oversight lab which is part of the Innovation Center for Artificial Intelligence (ICAI).

Your job
The Dutch government inspectorates play a critical role in safeguarding public interests such as food safety, a clean environment, and quality of education. To ensure effective oversight with a limited capacity at strategic and operational level, inspectorates need to work in a data-driven way and embed AI technology in their primary processes.

By joining the ICAI lab AI4Oversight, you join a community that collaborates to address AI challenges specific to the inspection domain leading to scientifically attested methods. The AI4Oversight lab connects the Human Environment and Transport Inspectorate (ILT), the Netherlands Labour Authority (NLA), the Inspectorate of Education (IvhO), Netherlands Food and Consumer Product Safety Authority (NVWA), Netherlands Organisation for Applied Scientific Research (TNO), Utrecht University and Leiden University. Collaboration between these organisations is seen as an essential element of our lab. Working together enables not only to develop new knowledge, but also to use each other’s expertise, to experiment together, to learn from each other and to bring theory to practice.

The execution of the research will be highly participatory. You will spend time at the offices of funding partners and have the opportunity to dive into the practical challenges and way of working of the partners. You will work together with data scientists of the inspectorates, who will contribute with practical experiences and use cases. Within the AI4Oversight Lab you will be part of a collaborative environment with at least five other PhD candidates, where you regularly engage in knowledge exchanges to strengthen cross-disciplinary collaboration.

Your work aims to advance risk classification beyond binary labels by learning interdependencies between inspection items using probabilistic graphical models like Bayesian networks. These models aim to support interactive inspections by prioritizing items dynamically, combining data-driven learning with expert knowledge to handle incomplete information effectively.

Your key responsibilities will be to:

• conduct original research in the field of learning graphical models from data for the purpose of risk-based inspection;
• publish and present scientific articles at international journals and conferences;
• collaborate with other PhD candidates in the AI4 Oversight lab, researchers at the partners’ data science labs, and the intended users and other stakeholders;
• contribute to the teaching tasks of the department (10-15% of your time).

Requirements:

You are equipped with a critical mindset and motivated to use your experience in education and research to make a valuable contribution to research in the field of artificial intelligence and machine learning. Next to that you have the following qualifications:

• a MSc degree in Artificial Intelligence, Data Science, Computer Science, Mathematics or a related field;
• demonstrable programming skills, preferably in Python;
• solid experience with machine learning, in particular with graphical models such as Bayesian networks;
• the ability to work with diverse stakeholders, such as industry professionals and academic researchers;
• proficiency in English (spoken and written);
• proficiency in Dutch is considered an advantage, as you will be working in close cooperation with Dutch organisations.

A background check may be part of the selection procedure.

Salary Benefits:

• A position for four years;
• 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.

36 - 40 hours per week

Princetonplein 5