Postdoc position in Singular Learning Theory for Machine Learning Models

Are you a PhD in Machine Learning Computer Science Mathematics Statistics Physics or a closely related field and want to join the mission of unlocking the geometry of artificial intelligence then come join us!

Join us

We are looking for a highly motivated postdoctoral researcher to join the mission of unlocking the geometry of artificial intelligence in the group of dr. Patrick Forré. If you want to join the mission of unlocking the geometry of artificial intelligence then please apply!

What you will do

Singular Learning Theory (SLT) is a mathematical framework for analysing statistical models that do not follow the classically made regularity assumptions (which would lead to asymptotic normality etc.). Such singular models include many models from statistical physics as well as almost all modern (overparameterized) machine learning models like probabilistic graphical models deep neural networks diffusion models transformers e.g. large language models etc. SLT is based on the geometrical understanding of the parameter space in relation to the statistical model. One of the main goals of SLT is to quantify the complexity of such models w.r.t. the data generating process (and some prior probability distribution). SLT and the estimation of such quantities has recently led to many applications ranging from model selection and uncertainty quantification over detecting phase transitions in machine learning models during training the finding of interpretable substructures to the explainability of general learning behaviour of such machine learning models etc.

In this project we want to build upon the recent developments in the field and either push the boundaries of SLT on the mathematical foundational theory side extend SLT to new learning frameworks (e.g. variational inference or reinforcement learning etc.) and/or apply it to modern machine learning models like large language models or diffusion models etc.

You are expected to:

• take an active role in the research project either in the development of the mathematical theory of SLT and/or through novel applications of SLT in the machine learning domain.
• publish and present your findings in academic peer-reviewed journals international workshops and/or conferences.
• support the teaching activities at the faculty (up to 10% of the time).

What we ask of you

• A PhD in Machine Learning Computer Science Mathematics Statistics Physics or a closely related field. (In case you have finished a PhD thesis and you are just awaiting your PhD defence please also apply.)
• Enthusiasm for the scientific process: formulating and investigating hypotheses either mathematically or by conducting experiments disseminating findings via writing and oral presentations etc.
• Experience in publishing academic papers in peer-reviewed journals and/or conferences.
• Professional command of English both written and spoken.
• Ability both to work independently as well as to cooperate and work effectively within a (possibly interdisciplinary) team of researchers.
• Experience in programming and software development. Familiarity with Python and statistical computing libraries like PyTorch or JAX etc. would be preferred.
• You are a motivational teacher with an encouraging teaching style.

What we offer you

We offer a temporary employment contract for 38 hours per week for a period of 18 months. The preferred starting date is as soon as possible and to be discussed.

The gross monthly salary based on 38 hours per week and dependent on relevant experience ranges between 3546 and 5538 (scale 10).This does not yet include the 8% holiday allowance and 83% year-end allowance which will come on top. The UFO profile Researcher/Onderzoeker 4 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.

You will work here

TheFaculty of Science (FNWI) has a student body of around 8000 as well as 1800 members of staff working in education research or support services. Researchers and students at the Faculty of Science are fascinated by every aspect of how the world works be it elementary particles the birth of the universe or the functioning of the brain.

The Korteweg-de Vries Instituut voor Wiskunde (KdVI) is the mathematical research institute of the Faculty of Science of the Universiteit van Amsterdam. The KdV Institute offers a stimulating scientific environment in which research focuses mainly within the research programmes (1) Algebra Geometry and Mathematical Physics (2) Pure Applied and Numerical Analysis and (3) Stochastics and (4) Discrete Mathematics and Quantum Information. It also provides the lecturers and instructors for the mathematics teaching within the Science Faculty. The KdV Institute participates in the NWO research clusters GQT STAR NDNS and DIAMANT and in the Gravity programme NETWORKS. There is formal (and informal) cooperation with the Centrum Wiskunde & Informatica (CWI) the VU University and with Eurandom in Eindhoven. KdVI counts about 40 staff members and 50 postdocs and PhD students.

This position will also be affiliated with the AI4Science Lab which originated out of the Amsterdam Machine Learning Lab (AMLab) at the Informatics Institute (IvI) and which is a cross-institute collaboration at the Faculty of Science aimed at bridging the gap between modern machine learning developments and their applications to the different areas of science.

If you feel the profile fits you and you are interested in the job we look forward to receiving your application. You can apply online via the button below. We accept applications until and including . The interviews are expected to take place in March 2026.

If you have any questions or do you require additional information Please contact:

• Dr. Patrick Forré Associate Professor of Stochastics KdVI

Applications should include the following information (all files besides your cv should be submitted in one single pdf file):

• a detailed CV including the months (not just years) when referring to your education and work experience.

• a list of publications.

• a letter of motivation including research statement describing your interests in the topic and potential avenues of research (e.g. an idea for an initial project);
• the names and email addresses of two references who can provide letters of recommendation (please do not include the letters themselves).
• a complete record of your courses including grades and an explanation of the grading system.
• a link to / a copy of the most relevant written work product. Examples: PhD or MSc thesis research paper (working draft or pre-print is acceptable) course project blog post etc.
• Optional: A letter providing any additional information not sufficiently highlighted by the other materials.

A knowledge security check can be part of the selection procedure.(for details:national knowledge security guidelines)