Summary
Radboud University is offering a PhD position in Physics-Informed Generative AI for Synthetic Energy Data. This NWO-funded SHARE project aims to develop AI models that generate realistic, privacy-preserving synthetic energy data crucial for grid planning and decision-making in the energy transition. The successful candidate will work with real-world data from Alliander, publish at leading machine learning venues, and contribute to tools with tangible impact on the Dutch energy sector.
PhD Position: Physics-Informed Generative AI for Synthetic Energy Data at Radboud University, Netherlands
Designation
PhD Candidate
Employment Details
| Employment | Gross Monthly Salary | Required Background | Organizational Unit |
|---|---|---|---|
| 1.0 FTE | €3,204 – €4,051 | Research University Degree | Faculty of Science |
Research Area
The core scientific contribution of this project (Work Package 3 of the SHARE project) involves developing physics-informed, domain-constrained generative models for energy-system data. Specific areas include:
- Designing and comparing deep generative approaches (VAEs, GANs, diffusion models/flow matching, Gaussian processes) for realistic load, generation, and voltage time series.
- Embedding physical constraints into generation, such as power-flow consistency (Kirchhoff’s laws), operational bounds (voltage limits, capacity, phase balance), and network topology through graph neural network architectures.
- Building validated benchmark datasets and an evaluation framework covering statistical fidelity, temporal and spatial structure, physical plausibility, and downstream task performance.
- Collaborating on integrating differential privacy into the generative pipeline.
- Contributing to an open-source synthetic data toolbox for DSOs, municipalities, and researchers.
Location
Nijmegen, Netherlands (Radboud University, Data Science section of the Institute for Computing and Information Sciences – iCIS)
Eligibility/Qualification
Candidates should meet the following criteria:
- Hold an MSc degree (or will obtain one before the starting date) in computer science, artificial intelligence, data science, applied mathematics, physics, electrical engineering, or a related field.
- Possess a solid background in machine learning; experience with deep generative models (VAEs, GANs, diffusion models) or probabilistic modeling is a strong plus.
- Have good programming skills in Python and experience with a deep learning framework such as PyTorch.
- Enjoy interdisciplinary work and interaction with privacy researchers, legal scholars, and energy-sector practitioners.
- Have a good command of spoken and written English.
- Prior knowledge of energy systems is not required.
Scholarship Description
This is a temporary employment contract of 1.5 years, with the possibility of extension by 2.5 years (total 4-year contract) upon positive performance evaluation. The position offers a starting gross monthly salary of €3,204, increasing to €4,051 in the fourth year (based on a 38-hour working week). Additional benefits include:
- 8% holiday allowance and an 8.3% end-of-year bonus.
- Extra days off (choice between 30 or 41 days of annual leave with full-time employment).
- Flexible working hours and various leave arrangements.
- Opportunity to compose part of employment conditions, e.g., exchange income for extra leave days or receive reimbursement for sports membership.
- 34% discount on sports and cultural activities at Radboud University.
- Good pension plan.
- Ample room and responsibility for talent development and training schemes.
- Opportunity to spend up to 10% of time on teaching activities.
How to Apply
Applications must be submitted via the provided apply button. Applicants should address their letter of application to Yuliya Shapovalova. The application form will specify required documents. In the motivation letter, applicants should address the following questions:
- Which generative modeling approach would be used as a starting point for energy time series on a physical network, why it would be chosen, and what the biggest challenge is expected to be (reasoning is key).
- A description of a proud software application or data analysis project (what it does, challenges, personal contribution; a link is optional).
- A one-paragraph description of the MSc thesis, written for a reader outside the applicant’s field.
The preferred start date for employment is 1 January 2027.
Last Date for Apply
25 October 2026
Apply Link
