Postdoc Scalable Graph Learning

Job description

Delft University of Technology (TU Delft) is seeking applications for a postdoctoral researcher in the area of Scalable Graph Learning, within the Department of Software Technology in the Faculty of Electrical Engineering, Mathematics, and Computer Science.

Graph machine learning (Graph ML) is a rapidly growing area of artificial intelligence (AI), driven by the widespread presence of graph-structured data across many real-world domains. Graph neural networks (GNNs) lie at the core of this field and have proven effective in a wide range of applications, including recommender systems, financial crime detection, cybersecurity, and network analysis.

This project focuses on scalable, parallel, distributed, federated, and hardware-accelerated training and inference of GNNs and graph transformers, with applications in the financial domain. In particular, it targets the analysis of financial transaction networks for the detection and prevention of financial crime. Robustness and resilience under data heterogeneity and adversarial conditions will also be investigated.

About the Research Group

The Scalable Graph Learning Group, led by Associate Professor Kubilay Atasu, is part of the Data-Intensive Systems Section. The group focuses on both theoretical and practical aspects of Graph Machine Learning, including:

• Algorithmic efficiency
• Expressiveness
• Scalability
• Real-world applications

The Department of Software Technology

The Department of Software Technology (ST) is one of the leading Dutch departments in research and academic education in computer science, employing over 150 people. The department is responsible for a large part of the curriculum of the bachelor’s and master’s programmes in Computer Science as well as the master’s programme in Embedded Systems. Its research topics are largely inspired by technical ICT problems in industry and society related to large-scale distributed processing, embedded systems, programming productivity, and web-based information analysis.

Job requirements

We are looking for a candidate who satisfies the following requirements:

• A PhD degree in Computer Science, Mathematics, Electrical Engineering, or a related discipline, with a PhD thesis conducted in the field of machine learning, deep learning, or parallel and distributed computing
• Experience in graph machine learning, federated learning, differential privacy, or adversarial robustness
• Hands-on experience with deep neural networks using PyTorch or TensorFlow, and preferably with GNNs using PyTorch Geometric or Deep Graph Library
• First-author publications at leading conferences in artificial intelligence, machine learning, security and privacy, or data management

Faculty of Electrical Engineering, Mathematics and Computer Science

The Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS) brings together three scientific disciplines. Combined, they reinforce each other and are the driving force behind the technology we all use in our daily lives. The faculty contributes to areas such as sustainable electricity systems, future chips and sensors, software technologies including AI, and applied mathematics. It offers an innovative environment with excellent labs and facilities, strong opportunities for ground-breaking research and innovative engineering education, and a strong international position.

Conditions of employment

• Duration of contract is 1 year temporarily with a possibility for extension.
• An excellent pension scheme via the ABP.
• The possibility to compile an individual employment package every year.
• Discount with health insurers on supplemental packages.
• Flexible working week.
• Every year, 232 leave hours (at 38 hours). You can also sell or buy additional leave hours via the individual choice budget.
• Plenty of opportunities for education, training and courses.
• Partially paid parental leave.
• Attention for working healthy and energetically with the vitality program.
• Support for relocation to the Netherlands through Coming to Delft Service, including information, events, and a Dual Career Programme for accompanying partners.

As part of knowledge security, TU Delft conducts a risk assessment during recruitment to help prevent the unwanted transfer of sensitive knowledge and technology. The assessment is based on information provided by candidates, such as their motivation letter and CV, and takes place at the final stages of the selection process. When the outcome is negative, the candidate will be informed. The processing of personal data in this context is carried out on the legal basis of the GDPR: performing a public task in the public interest.