CentraleSupélec opens 24-month graph-ML postdoc on EHRs
TL;DR
- A 24-month postdoc at CentraleSupélec, Inria Saclay and Paris-Saclay opens for graph machine learning on Electronic Health Records, starting early 2027.
- Project builds graph neural networks, self-supervised learning on graphs and generative models to learn patient representations from EHRs for clinical prediction.
- Supervisor Fragkiskos Malliaros screens applications on a rolling basis; a math-strong PhD with Python and PyTorch is required.
A 24-month postdoc has opened at CentraleSupélec, Centre Inria de Saclay and Université Paris-Saclay for graph machine learning on Electronic Health Records, starting in early 2027. The PDF listing on Drive names Fragkiskos Malliaros, a full professor at CentraleSupélec and researcher in the OPIS team at Inria Saclay, as supervisor.
Scope runs through graph neural networks, self-supervised learning on graphs and generative models, applied to learn patient representations from EHRs for clinical prediction and healthcare research. A companion graph-learning call from the same lab on ml-news uses the same vocabulary: "Development of Graph Neural Network (GNN) architectures, focusing on expressiveness and scalability" alongside "Self-supervised learning on graphs," with biomedical applications among the stated areas.
Candidates need "A recent Ph.D. degree in Computer Science, Mathematics, Engineering, Physics, or Biology with a strong mathematical background," plus Python and PyTorch. Materials go by email to Malliaros on a rolling basis. Two researchers we follow had already shared the link before we logged it.
Shared on Bluesky by 2 AI experts
-
🏹 Job alert: Postdoctoral Researcher Position on Graph Machine Learning for Healthcare 📍 Paris 🇫🇷 ⏰ 31 December 🔗 https://drive.google.com/file/d/10YY4EvBOKe8F54y_M55jO9BHeH4v0btQ/view
View on Bluesky →
Originally reported by drive.google.com
Read the original article →Original headline: Postdoc_Position_CentraleSupelec_Graph_ML_Healthcare_2026.pdf