En poursuivant votre navigation sur ce site, vous acceptez le dépôt de cookies dans votre navigateur. (En savoir plus)
Portail > Offres > Offre UMR6074-NICKER-007 - Ingénieur.e (H/F) en apprentissage sur graphes

Engineer (M/F) in Graph Machine Learning

This offer is available in the following languages:
- Français-- Anglais

Date Limite Candidature : vendredi 9 janvier 2026 23:59:00 heure de Paris

Assurez-vous que votre profil candidat soit correctement renseigné avant de postuler

Informations générales

Intitulé de l'offre : Engineer (M/F) in Graph Machine Learning (H/F)
Référence : UMR6074-NICKER-007
Nombre de Postes : 1
Lieu de travail : RENNES
Date de publication : vendredi 19 décembre 2025
Type de contrat : IT en contrat CDD
Durée du contrat : 6 mois
Date d'embauche prévue : 1 avril 2026
Quotité de travail : Complet
Rémunération : between 2496€ and 2662€ depending on experience
Niveau d'études souhaité : BAC+5
Expérience souhaitée : 1 à 4 années
BAP : E - Informatique, Statistiques et Calcul scientifique
Emploi type : Ingenieure statisticienne ou ingenieur statisticien

Missions

Several concepts of Riemannian geometry have recently found applications in graph Machine Learning, such as the Ollivier-Ricci curvature. A recent example is the delta-hyperbolicity, which measures how graphs locally look like a tree, which has found applications in treating over-squashing in Graph Neural Networks. However, a fundamental limit of this notion is its combinatorial nature, which limits its integration in ML pipelines. Recently, a differentiable surrogate of delta-hyperbolicity has been proposed [1], and studied theoretically.

The goal of this project is to integrate and benchmark this new notion in Graph ML and Graph Neural Networks.

[1] Pierre Houedry, Nicolas Courty, Florestan Martin-Baillon, Laetitia Chapel, and Titouan Vayer. Bridging arbitrary and tree metrics via differentiable gromov hyperbolicity. In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025

Activités

Integrate and benchmark delta-hyperbolicity in Graph ML and Graph Neural Networks, study the scalability of the training process.

Compétences

Good skills with Pytorch. Experience with graph Machine Learning and Pytorch Geometric is a plus.

Contexte de travail

IRISA is today one of the largest French research laboratory (more than 850 people) in the field of computer science and information technologies.
Structured into seven scientific departments, the laboratory is a research center of excellence with scientific priorities such as bioinformatics, systems security, new software architectures, virtual reality, big data analysis and artificial intelligence.

Located in Rennes, Lannion and Vannes, IRISA is at the heart of a rich regional ecosystem for research and innovation and is positioned as the reference in France with an internationally recognized expertise through numerous European contracts and international scientific collaborations.

Focused on the future of computer science and necessarily internationally oriented, IRISA is at the very heart of the digital transition of society and of innovation at the service of cybersecurity, health, environment and ecology, transport, robotics, energy, culture and artificial intelligence.

Contraintes et risques

NA