CentraleSupélec, Inria Saclay, and Université Paris-Saclay in France are inviting applications for a 24-month Postdoctoral Researcher Position in Graph Machine Learning for Healthcare, starting in early 2027. The position focuses on developing graph-based machine learning methods to learn patient representations from Electronic Health Records (EHRs), with applications in clinical prediction and healthcare research. Candidates should hold a Ph.D. in Computer Science, Engineering, Applied Mathematics, Statistics, or a related field, with a strong background in machine learning and deep learning.
Important Dates / Deadline
- Application Deadline: November 14, 2026 (standardized deadline set 15 calendar days after the current date because the announcement does not specify a fixed application deadline).
- Application Review: Rolling basis until the position is filled.
- Expected Start Date: Early 2027.
- Position Duration: 24 months.
Organization
- Host Institution: CentraleSupélec, Université Paris-Saclay.
- Research Partner: Inria Saclay, OPIS Team.
- Research Laboratory: Centre for Visual Computing (CVN).
- Research Project: ANR RHU Innov4-ePiK.
- Project Lead Institution: Institut Imagine.
- Research Advisor: Fragkiskos Malliaros.
Location / Study Destination
France: CentraleSupélec, Université Paris-Saclay, Paris-Saclay research cluster, near Paris. The research environment is approximately 45 minutes by train from central Paris.
Who Can Apply
Applicants should meet the following eligibility criteria:
- Hold a Ph.D. in Computer Science, Engineering, Applied Mathematics, Statistics, or a related discipline.
- Have a solid academic background in machine learning and deep learning.
- Demonstrate an interest in graph-based learning methods, particularly Graph Neural Networks (GNNs).
- Have a strong publication record in machine learning or related research areas.
- Be capable of conducting independent research and collaborating with multidisciplinary research teams.
Key Benefits / Salary / Funding
- Contract Duration: 24 months.
- Research Funding Context: The position is part of the ANR RHU Innov4-ePiK project, led by Institut Imagine.
- Opportunity to conduct fundamental research in graph machine learning and apply advanced methods to real-world healthcare challenges.
- Access to a multidisciplinary research environment involving machine learning researchers, clinicians, and medical informatics experts.
- Opportunities to develop and validate machine learning methodologies using real-world clinical data.
- Collaboration with Ph.D. and Master’s students working on related research topics.
- Opportunities for academic collaboration with research partners in France and internationally.
Main Requirements
Academic Qualifications and Research Experience
- Ph.D. in Computer Science, Engineering, Applied Mathematics, Statistics, or a related field.
- Strong knowledge of machine learning and deep learning methodologies.
- Demonstrated research productivity through publications in machine learning or related fields.
- Interest in graph representation learning and Graph Neural Networks.
Technical Skills
- Proficiency in Python programming.
- Experience with deep learning frameworks, particularly PyTorch.
- Knowledge of graph-based machine learning approaches.
- Strong analytical and problem-solving abilities.
- Effective scientific communication and research collaboration skills.
Research Responsibilities
The selected researcher will investigate graph machine learning methods for healthcare applications, focusing on:
- Graph Representation Learning: Developing effective representations of patients using graph-based learning techniques.
- Graph Neural Networks: Exploring GNN architectures for modeling relationships within healthcare data.
- Self-Supervised Learning: Investigating methods for learning patient representations from complex clinical datasets.
- Generative Models: Exploring generative approaches for healthcare data representation learning.
- Electronic Health Records: Addressing heterogeneous and multimodal information, missing observations, and complex temporal dependencies.
- Clinical Prediction: Developing transferable patient representations to support downstream clinical prediction tasks.
- Multidisciplinary Research: Collaborating with clinicians and medical informatics experts to evaluate methods using real-world clinical data.
How to Apply
Interested candidates should submit their applications through the official online application form.
Application Form: https://shorturl.at/EGbo5
Application Steps:
- Prepare an updated academic CV, including a complete list of publications.
- Write a brief motivation letter explaining your research interests and suitability for the position.
- Provide the names and contact details of two academic or professional references.
- Submit the required information and documents through the online application form.
Applications will be reviewed on a rolling basis until the position is filled.
For inquiries, contact:
Fragkiskos Malliaros
Email: fragkiskos.malliaros@centralesupelec.fr
Documents Needed
Applicants must prepare the following documents:
- Curriculum Vitae (CV): An updated academic CV, including a list of research publications.
- Motivation Letter: A brief letter, maximum one page, describing research interests and explaining suitability for the position.
- References: Names and contact information of two references.
Important Notes
- The research position is associated with the ANR RHU Innov4-ePiK project, which aims to advance research and innovation in epilepsy.
- The research will focus on graph machine learning approaches for patient representation learning using Electronic Health Records.
- The selected candidate will join the Centre for Visual Computing, a joint laboratory between CentraleSupélec and Inria Saclay.
- The position offers opportunities to work with clinical researchers and medical informatics specialists on real-world healthcare challenges.
- Applications are evaluated on a rolling basis, and recruitment will continue until the position is filled.
- Candidates are encouraged to apply early.
