Publisher
source

Radboud University

Just Landed

PhD Position in Physics-Informed Generative AI for Synthetic Energy Data Radboud University in Netherlands

Degree Level

PhD

Field of study

Computer Science

Funding

This is a paid PhD employment position at 1.0 FTE. The contract is initially for 1.5 years and, after positive evaluation, can be extended by 2.5 years for a total of 4 years. Gross monthly salary starts at €3,204 and rises to €4,051 in the fourth year, plus an 8% holiday allowance, an 8.3% end-of-year bonus, and extra annual leave.

Deadline

Oct 25, 2026

Country flag

Country

Netherlands

University

Radboud University

Social connections

How do I apply for this?

Sign in for free to reveal details, requirements, and source links.

Apply for this position

Keywords

Computer Science
Electrical Engineering
Information Technology
Mathematics
Time Series Analysis
Data Privacy
Gaussian Processes
Generative Modeling
Physics
Renewable Energy Systems

Suggested positions

About this position

Radboud University in Nijmegen, the Netherlands is recruiting a PhD candidate for the NWO-funded SHARE project on physics-informed generative AI for synthetic energy data. The project sits in the Data Science section of the Institute for Computing and Information Sciences (iCIS), Faculty of Science, and focuses on building realistic, privacy-preserving synthetic datasets for energy-system planning and decision-making.

The research topic combines computer science, electrical engineering, physics, and mathematics. You will develop deep generative models for load, generation, and voltage time series on physical networks, compare approaches such as VAEs, GANs, diffusion models, flow matching, and Gaussian processes, and embed power-flow consistency, operational bounds, and graph-based network structure into the generation process. The work also includes benchmark dataset creation, evaluation frameworks, and an open-source synthetic data toolbox.

The project is highly interdisciplinary and involves collaboration with privacy researchers, legal scholars, and energy-sector practitioners. You will work with real operational data from Alliander and contribute to applications such as congestion forecasting, spatial energy planning, and flexibility assessment. The consortium includes Radboud University, the Dutch Open University, DSO Alliander, VSL, Zenmo, Bronscode, and the Municipality of Nijmegen.

Supervision is by Dr Yuliya Shapovalova and Prof. Tom Heskes. The role includes up to 10% teaching support in computing science courses. The position is a 1.0 FTE paid PhD employment contract: 1.5 years initially, extendable by 2.5 years after positive evaluation. Salary starts at €3,204 gross per month and rises to €4,051 in year four, plus holiday allowance, end-of-year bonus, and generous leave.

Applicants should have an MSc degree, or expect to obtain one before the start date, in computer science, artificial intelligence, data science, applied mathematics, physics, electrical engineering, or a related field. Strong machine learning skills and Python/PyTorch experience are expected; prior energy-systems knowledge is not required. The preferred start date is 1 January 2027. Application deadline: 25 October 2026.

Funding details

This is a paid PhD employment position at 1.0 FTE. The contract is initially for 1.5 years and, after positive evaluation, can be extended by 2.5 years for a total of 4 years. Gross monthly salary starts at €3,204 and rises to €4,051 in the fourth year, plus an 8% holiday allowance, an 8.3% end-of-year bonus, and extra annual leave.

What's required

Applicants should hold an MSc degree, or expect to obtain one before the start date, in computer science, artificial intelligence, data science, applied mathematics, physics, electrical engineering, or a related field. A solid background in machine learning is required; experience with deep generative models (VAEs, GANs, diffusion models) or probabilistic modelling is a strong plus. Good programming skills in Python and experience with a deep learning framework such as PyTorch are expected. Candidates should enjoy interdisciplinary work with privacy researchers, legal scholars, and energy-sector practitioners, and have good spoken and written English. Prior knowledge of energy systems is not required.

How to apply

Apply only via the application button on the Radboud University vacancy page. Address your application letter to Yuliya Shapovalova and include the documents requested in the application form. In your motivation letter, answer the three questions listed in the post.

More information can be found here

Ask ApplyKite AI

Start chatting
Can you summarize this position?
What qualifications are required for this position?
How should I prepare my application?