Postdoctoral Position on Mathematical Foundations for Explainable AI
Postdoctoral Position on Mathematical Foundations for Explainable AI
UvA - University of Amsterdam
Amsterdam, Netherlands
This is what you will do
Explainable AI (XAI) is a hot topic in machine learning to provide insights into the decisions of complicated machine learning models. For instance, why does a machine learning model predict that it is unsafe to discharge a certain patient from the intensive care? Or which characteristics make a machine learning model flag a certain bank transfer as potential money laundering? But XAI has received heavy criticism, because of exaggerated claims, lack of methodological rigor, and unreliability. More fundamentally, there is no agreement on central issues: What is a good explanation? When can we trust explanations? The aim of this project is to address these issues by developing mathematical foundations for XAI, and proving performance guarantees for new explanation methods using the same standards as in other parts of machine learning theory. As a postdoctoral researcher, you will be collaborating closely with the PhD students and Tim van Erven, as well as developing your own research initiatives and (inter)national network.
Tasks and responsibilities:
- Conduct research within the specified project, as described above.
- Interact actively with the PhD students.
- Disseminate your research findings through publications in academic journals or peer-reviewed international conference proceedings, and through presentations at international conferences.
- Engage in research collaborations locally and/or internationally.
- Participate in the department’s educational programs, by teaching one single-semester course per year.
What we ask of you
We are looking for an enthusiastic and driven candidate who meets the following requirements:
Your experience and profile:
- PhD in machine learning theory, with thesis submitted before the start of the Postdoctoral position.
- Publications on machine learning theory in proceedings of international machine learning conferences (COLT, ALT, ICML, NeurIPS, AIStats, UAI); or in international machine learning journals (JMLR, Machine Learning); or comparable venues.
- Interests: You should have a strong interest to develop new learning-theoretic directions in explainable AI.
- Communication skills: You should have excellent written and verbal communication skills in English.
- Teamwork and independence: You should be highly motivated and committed to your research. While you should be able to work independently, you should also have a cooperative attitude and be willing to collaborate with the team members or other researchers.
- Teaching: You should be able to contribute to the department’s educational programs.
- Good programming skills are a plus, as is prior knowledge of explainable AI.
© EuroJobsites 2025
