Postdoctoral Position in Deep Learning at Aix-Marseille University

A postdoctoral fellow position on deep learning is available at the University of Aix-Marseille (AMU) and the Computer Science Lab of Marseille (LIS). The successful candidate will work within the framework of the French National Research Agency (ANR) project Deep in France (DIF).


The candidate will be working on building "green" deep learning models that are limited in memory and computation power while preserving good predictive performance. On an applicative side a focus of the project will concern spatio temporal data and video forecasting. In addition to deep learning and video forecasting a list of topics of particular interest includes low-rank tensor decompositions and kernel methods. Suitable candidates are experts in one of these topics, and eager to work with experts of the others.

The successful candidate will join the machine learning team Qarma located at the center of Mathematics and Computer Science in Marseille. Situated in the southeast of France, Marseille is a Mediterranean city that enjoys a nice climate all year round and offers beautiful landscapes between sea and Calanques. The research conducted in the Qarma team covers both fundamental and applied aspects of machine learning. The working language of the team is English. The selected candidate will be working directly with Thierry Artières, Stéphane Ayache and Hachem Kadri


Candidates should have:
  • A PhD in computer science, applied mathematics or electrical engineering, with a focus on machine learning.
  • Experience in deep learning model development using one or more software tools such as TensorFlow, Theano, PyTorch, etc.
  • A strong track record of published research.
  • A strong motivation to explore new techniques and concepts.

Application process

The position is expected to be available starting September 2018. Applications will be continuously received until the position is filled. Applications and further questions regarding the position should be addressed to and