École Normale Supérieure
Just Landed
Posted Yesterday
Postdoctoral Researcher in Mathematics of Machine Learning — PERSNET Ecole Normale Supérieure in France
Degree Level
Postdoc
Field of study
Stochastic Processes
Funding
Available
Deadline
Nov 30, 2026
Country
France
University
École Normale Supérieure
Apply for this position
You'll sign in first, then continue in your ApplyKite dashboard.
Keywords
Suggested positions
About this position
Applications are invited for an 18-month, full-time postdoctoral research position in the mathematical and statistical foundations of machine learning at École normale supérieure – PSL in Paris.
The position is hosted by the Département de mathématiques et applications (DMA), within the Probability and Statistics team and the ENS-PSL Center for Data Science, and is supported by the PERSNET project in the French PEPR Artificial Intelligence programme, funded by France 2030. The postdoc will work with Eddie Aamari and develop a research programme jointly, aligned with the scientific scope of PERSNET and the candidate’s expertise and interests.
Research directions include topological and geometric analysis of neural networks; transformers, attention dynamics, tokenization and learned representations; generative modelling on manifolds and stratified spaces; diffusion and score-based models; drifting models and kernelized transport; gradient flows associated with maximum mean discrepancy and reproducing kernel Hilbert spaces; nonlocal partial differential equations; RKHS geometry; kernel mean embeddings; and geometric statistical testing.
The main responsibilities are to conduct original research, prepare scientific publications, present findings at seminars and conferences, and contribute to the scientific activities of the host team and the PERSNET project. Applicants should have a PhD or equivalent and a strong background in relevant mathematical areas such as probability, statistics, geometric inference, optimal transport, PDEs, stochastic processes, topological data analysis, kernel methods, or mathematical machine learning.
Experience with generative models, transformers, or numerical experiments is welcome but not required. The post is based in Paris, France, with a deadline of 30 November 2026 at 12:00 (Europe/Paris). Applications are submitted by email to Eddie Aamari.
Funding details
Available
What's required
Applicants should have a PhD or equivalent in mathematics, statistics, or a closely related field. A strong mathematical background in one or more relevant areas is expected, including probability, statistics, geometric inference, optimal transport, partial differential equations, stochastic processes, topological data analysis, kernel methods, or mathematical machine learning. Candidates should be able to develop rigorous mathematical arguments, pursue original research with increasing independence, and collaborate and communicate effectively in English. Prior experience with generative models, transformers, or numerical experiments is welcome but not required; expertise in all listed research directions is not expected.
How to apply
Send an application by email to [email protected]. Use the subject line indicating the position title. Follow any further instructions on the project or lab webpage if provided.
Make your next move.
Prepare your application
Review drafts and confirm requirements with the university.
Make your next move.
Prepare your application
Review drafts and confirm requirements with the university.