Annuaire
Poste de Post-doctorat en Apprentissage Statistique
Applications are invited for a postdoctoral fellowship at ENS Lyon in the field of machine learning.
The position is part of the research project "Neural networks for homomorphic encryption", funded by Inria. Fully homomorphic encryption (FHE) enables computations to be performed directly on encrypted data without knowledge of the deciphering key, offering significant potential for privacy-preserving deep learning. However, conventional neural networks are not well-suited to the computational constraints of FHE. The project aims to develop more efficient neural network architectures tailored for encrypted computations.
The postdoctoral researcher will be supervised by Jean-Christophe Mourrat, in collaboration with Guillaume Hanrot and Damien Stehlé (Cryptolab, on leave from ENSL), as well as Aurélien Garivier, Rémi Gribonval and the Inria Ockham team.
The position is for two years, with a possible extension of one additional year. The ideal start date is September 1, 2026. The fellowship includes financial support for conference travel and collaborator visits. There are no teaching obligations, though teaching opportunities can be arranged if desired.
The ideal candidate should have experience with machine learning, particularly in deep learning or related areas. No prior knowledge of cryptography is required. Expertise in optimization or efficient algorithm design will be considered an asset.
Applications should include a CV, a list of publications and a research statement. Applicants should also arrange for two or three letters of recommendation to be sent directly by each letter writer.
For applying before December 12 : (here)