[bull-ia] PhD in Human-machine interactions: « Hierarchical Imitation Learning for Dialogue »

PhD in Human-machine interactions: « Hierarchical Imitation Learning for Dialogue »


We are looking for a PhD student, interested in novel technologies and in their evolution, to work on Hierarchical Imitation Learning for Dialogue systems.

The goal is to study imitation learning to allow virtual agents to learn to communicate by imitating humans.


The candidate will join the NADIA (Natural Dialogue Interaction) team and will also work in collaboration with PROF (PROFiling and datamining) team at Orange-Labs,

the R&D division of Orange at Lannion, Brittany (a charming city next to the sea: http://www.bretagne-cotedegranitrose.com/, https://www.lannion.bzh/).

For her/his diploma, the PhD student will be registered at Avignon University, with LIA (Laboratoire d’Informatique d’Avignon).


The candidate must hold a Master’s degree in Computer Science, Mathematics, Engineering or any related field, with a high mathematical level (optimisation, statistics and probability theory).

She/he should be able to work in multidisciplinary projects, collaborating with others while being able to work autonomously on her/his own tasks.


Good programming skills are absolutely necessary.  Experience in Machine Learning, reinforcement learning and AI is desired,

as well as mastering Deep-Learning tools such as Torch, pyTorch, TensorFlow or Keras.

Fluent English is required, while knowledge of French is not mandatory.


To apply submit your cv and cover letter to Orange-Jobs:  https://orange.jobs/jobs/offer.do?joid=81711&lang=fr


For further information please contact Dr. Lina Rojas (linamaria.rojasbarahona@orange.com)



Lina Rojas

Senior Research Engineer/Ingénieure de recherche senior AI&Dialogue
tél. +33 (0)2 96 07 04 10



_________________________________________________________________________________________________________________________ Ce message et ses pieces jointes peuvent contenir des informations confidentielles ou privilegiees et ne doivent donc pas etre diffuses, exploites ou copies sans autorisation. Si vous avez recu ce message par erreur, veuillez le signaler a l’expediteur et le detruire ainsi que les pieces jointes. Les messages electroniques etant susceptibles d’alteration, Orange decline toute responsabilite si ce message a ete altere, deforme ou falsifie. Merci. This message and its attachments may contain confidential or privileged information that may be protected by law; they should not be distributed, used or copied without authorisation. If you have received this email in error, please notify the sender and delete this message and its attachments. As emails may be altered, Orange is not liable for messages that have been modified, changed or falsified. Thank you.