.jobdescription td { padding: 0 5px; } .jobdescription * { border: none !important; border-width: 0 !important; font-size: 12px !important; font-family: Arial, Helvetica, sans-serif !important; color: black !important; } .jobdescription h1 b, .jobdescription h2 b, .jobdescription h3 b, .jobdescription h4 b, .jobdescription h1, .jobdescription h2, .jobdescription h3, .jobdescription h4 { font-size: 14px !important; font-weight: bold; margin-bottom: 0.5em !important; }
#search-wrapper{display:none;}
/* TUDelft Sidebar style */ .jobColumnTwo .joblayouttoken { background: #e3e3e3; color: #011b3c; padding: 0 20px 5px !important; } .jobColumnTwo .joblayouttoken .joblayouttoken-label { color: #039fd8; font-weight: bold; } .jobColumnTwo .joblayouttoken.marginTopLarge { padding: 20px 20px 5px 20px !important; } .jobColumnTwo .joblayouttoken.marginBottomLarge { padding: 0 20px 20px 20px !important; }
/* TU Delft full-width header image */ .topleft.verticallyscaled.backgroundimage.large-image-component { height: 0 !important; } div[role='img'] .topleft.scaled.large-image-component{ height: 0 !important; position: absolute; padding-top: 20% !important; background-position: center !important; top: 50px; } div.job{ position: relative; padding-top: 26% !important; } /* Fix voor niet werkende knop */ div.jobTitle{ z-index: 2; position: relative; margin-top: 5px; }
Postdoc Trustworthy Graph Machine Learning
Trustworthy Graph Machine Learning for Population Scale Networks
Job description
We invite applications for a postdoctoral researcher to work on fundamental techniques for trustworthy graph machine learning for the analysis of population-scale networks. The position focuses on two pillars of trustworthiness: explainability and privacy-preserving learning.
This research direction connects closely to ongoing work by Dr. Megha Khosla on trustworthy graph machine learning, especially on the relationship between transparency and privacy in graph-based models. Population-scale network data are highly relational and often sensitive. Graph models for such data must therefore be accurate, interpretable and designed to reduce privacy risks.
A central aim of the position is to develop explainability methods for graph machine learning as a form of decision support. These methods should help researchers understand both model behaviour and the underlying data. They should explain why a model makes a prediction, what structural or demographic patterns the model captures, and when its decisions are reliable enough to support scientific interpretation or decision-making.
At the same time, explanations and learned graph representations can themselves reveal sensitive information. In population-scale networks, privacy risks may arise from rare individuals, sensitive attributes, neighbourhood structures etc.The postdoc will therefore investigate how explanations and graph learning methods can be made privacy-aware. This may include studying privacy risks in develoed models, designing explanations that avoid unnecessary disclosure, or developing new privacy-preserving graph learning techniques.
The project is funded by Macroscope, a Dutch national research infrastructure for studying social change, misinformation and trust at population scale.
We are especially interested in candidates with strong expertise in either explainable graph machine learning or privacy-preserving graph learning, together with a willingness to collaborate across the other area.
You will work with the task PI, Dr. Megha Khosla, and her team of PhD and Master’s students. You will also collaborate with scientists from different fields across the Macroscope project, including computer science and computational social science. You will also get opportunities to expand your research network within the Computer Science departments and across the broader TU Delft research community.
Job requirements
PhD in computer science, AI, machine learning, data science, network science, computational social science, or a related field.
Expertise in either explainable graph machine learning or privacy-preserving graph learning.
Willingness to develop expertise across the other area.
Strong programming skills in Python, with experience using tools such as PyTorch, PyTorch Geometric, DGL, NetworkX, or scikit-learn.
Engineering skills and willingness/patience to work with large, noisy datasets, including preprocessing, pipeline development, and scalable evaluation.
Ability to work in an interdisciplinary team and communicate research clearly in English.
TU Delft (Delft University of Technology)
Working at TU Delft means contributing to solutions that really make a difference.
For over 180 years, we have been training engineers who make an impact worldwide in companies, government bodies, or as entrepreneurs. Our alumni turn knowledge into concrete solutions for the challenges of today and tomorrow. These challenges are changing rapidly. That is why we focus on themes such as energy, climate, digitalisation, artificial intelligence (AI), and smart mobility every day. Our education and research are directly aligned with what society needs now and in the future.
At TU Delft, our people make the difference. With their knowledge and curiosity, our staff provide a high-quality education and conduct pioneering research that extends beyond the campus. You will have the opportunity to take the initiative, work with others, and grow as a professional. Working at TU Delft means join an international community of professionals and students. Together, we create knowledge, innovations, and solutions that help move the world forward.
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. Technology such as the electricity grid, which our faculty is helping to make completely sustainable and future-proof. At the same time, we are developing the chips and sensors of the future, whilst also setting the foundations for the software technologies to run on this new generation of equipment – which of course includes AI. Meanwhile we are pushing the limits of applied mathematics, for example mapping out disease processes using single cell data, and using mathematics to simulate gigantic ash plumes after a volcanic eruption. In other words: there is plenty of room at the faculty for ground-breaking research. We educate innovative engineers and have excellent labs and facilities that underline our strong international position. In total, more than 1000 employees and 4,000 students work and study in this innovative environment.
, Mathematics and Computer Science.
Conditions of employment
Duration of contract is 2 years Temporary
A job of 38 hours per week.
Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities.
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.
Will you need to relocate to the Netherlands for this job? TU Delft is committed to make your move as smooth as possible! The HR unit, Coming to Delft Service, offers information on their website to help you prepare your relocation. In addition, Coming to Delft Service organises events to help you settle in the Netherlands, and expand your (social) network in Delft. A Dual Career Programme is available, to support your accompanying partner with their job search in the Netherlands. .
Additional information
If you would like more information about this vacancy or the selection procedure, please contact Dr. Megha Khosla, via
[email protected].
Application procedure
Are you interested in this vacancy? Please apply no later than 26 July 2026 upload the following documents:
CV
Motivational letter
Research statement describing your own ambitions for the research line you would like to pursue, and explaining how this position would help you develop and achieve those ambitions.
You can address your application to Dr. Megha Khosla.
Please note:
You can apply online. We will not process applications sent by email and/or post.
As part of knowledge security, TU Delft conducts a risk assessment during the recruitment of personnel. We do this, among other things, to prevent the unwanted transfer of sensitive knowledge and technology. The assessment is based on information provided by the candidates themselves, such as their motivation letter and CV, and takes place at the final stages of the selection process. When the outcome of the assessment is negative, the candidate will be informed. The processing of personal data in the context of the risk assessment is carried out on the legal basis of the GDPR: performing a public task in the public interest. You can find more information about this assessment on our website about knowledge security.
Please do not contact us for unsolicited services.
Faculty/Department: Faculty of Electrical Engineering, Mathematics & Computer Science
Salary range: €3546 - €5538
Submission is possible until: 26 Jul 2026
.videocomponenta2f51048d3f8cbf3 a{ border: 1px solid transparent; } .videocomponenta2f51048d3f8cbf3 a:focus{ border: 1px dashed #00a6d6 !important; outline: none !important; }
