PhD Position: Physics-Informed Generative AI for Synthetic Energy Data

Radboud International; Netherlands; On-site; EUR 38,000 - 49,000; Full time

Benefits offered by this job

Holiday allowance 8%

End-of-year bonus 8.3%

Extra leave days 30 or 41

Job summary

Radboud University is seeking a PhD candidate to develop physics-informed generative models for energy-system data, using real-world data from Alliander and collaborating with privacy researchers. You will publish at top ML venues and contribute to an open-source toolbox used by DSOs and researchers in the Netherlands.

The role involves close collaboration with other researchers, on-site work in Nijmegen, and a focus on machine learning methods including VAEs, GANs, diffusion models, and

Qualifications

• MSc degree in computer science, artificial intelligence, data science, applied mathematics, physics, electrical engineering, or related field.
• Strong background in machine learning; deep generative models or probabilistic modeling is a plus.
• Proficient Python programming and PyTorch experience.
• Enjoys interdisciplinary work with privacy researchers and energy practitioners.
• Good command of spoken and written English.

Responsibilities

• Develop physics-informed, domain-constrained generative models for energy-system data.
• Compare deep generative approaches (UAEs, GANs, diffusion models, flow matching) and GP methods.
• Embed physical constraints like power-flow consistency and network topology.
• Publish results at leading ML venues and build open-source tools.
• Collaborate with PhD candidate and postdoctoral researcher on privacy integration.

Skills

Python

PyTorch

English

Interdisciplinary collaboration

Education

MSc degree (CS/AI/DS/Math/Physics/EE)

Tools

PyTorch

Job description

Organisation/Company Radboud University Research Field Computer science » Modelling tools Computer science » Programming Engineering » Computer engineering Engineering » Electrical engineering Researcher Profile First Stage Researcher (R1) Application Deadline 25 Oct 2026 - 22:59 (UTC) Country Netherlands Type of Contract Temporary Job Status Not Applicable Hours Per Week 38.0 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

Can you help unlock the data needed for the energy transition? In the NWO-funded SHARE project, you will develop AI models that generate realistic, privacy-preserving synthetic energy data for grid planning and decision-making. Working with real-world data from Alliander, you will publish at leading machine learning venues while building tools with tangible impact on the Dutch energy sector. The Dutch energy transition depends on data that almost no one is allowed to see. Distribution system operators (DSOs), municipalities and energy communities need high-resolution grid and consumption data to plan grid reinforcements, heat networks and local flexibility, but privacy law (GDPR), commercial sensitivity and regulatory uncertainty keep this data locked away. Hence, critical infrastructure decisions are being made with incomplete information. Synthetic data offers a way out: realistic-but-artificial datasets that preserve the statistical, temporal and physical structure of real energy data without identifying real households or companies. But energy data is not like images or text: it consists of time series living on a physical network, governed by power-flow equations. Off-the-shelf generative models produce data that looks plausible but violates physics and is therefore of limited use for grid planning. As a PhD candidate you will develop physics-informed, domain-constrained generative models for energy-system data, the core scientific contribution of the SHARE project (Work Package 3). More concretely, your work will involve the following: You will design and compare deep generative approaches, UAEs, GANs, diffusion models/flow matching, and Gaussian processes for realistic load, generation and voltage time series. You will embed physical constraints into generation: power-flow consistency (Kirchhoff's laws) as soft or hard constraints, operational bounds (voltage limits, capacity, phase balance), and network topology through graph neural network architectures. You will build validated benchmark datasets and an evaluation framework covering statistical fidelity, temporal and spatial structure, physical plausibility and downstream task performance (e.g. train-synthetic-test-real forecasting). You will collaborate with a fellow PhD candidate and a postdoctoral researcher on integrating differential privacy into the generative pipeline, balancing privacy guarantees against data utility. You will contribute to an open-source synthetic data toolbox that DSOs, municipalities and researchers across the Netherlands will actually use.

• You will design and compare deep generative approaches, UAEs, GANs, diffusion models/flow matching, and Gaussian processes for realistic load, generation and voltage time series.
• You will embed physical constraints into generation: power-flow consistency (Kirchhoff's laws) as soft or hard constraints, operational bounds (voltage limits, capacity, phase balance), and network topology through graph neural network architectures.
• You will build validated benchmark datasets and an evaluation framework covering statistical fidelity, temporal and spatial structure, physical plausibility and downstream task performance (e.g. train-synthetic-test-real forecasting).
• You will collaborate with a fellow PhD candidate and a postdoctoral researcher on integrating differential privacy into the generative pipeline, balancing privacy guarantees against data utility.
• You will contribute to an open-source synthetic data toolbox that DSOs, municipalities and researchers across the Netherlands will actually use.

This is research with a direct route to impact: you will work with real operational data from Alliander, with regular on-site visits and direct access to the practitioners who will use your models for congestion forecasting, spatial energy planning and flexibility assessment. You will publish at top machine learning venues while producing open datasets and tools with tangible societal impact. You will be expected to spend a small part of your time (up to 10%) on teaching activities, such as assisting in courses of our computing science programmes. Would you like to learn more about what it’s like to pursue a PhD at Radboud University? Visit the page about working as a PhD candidate .

• You 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.
• You have a solid background in machine learning; experience with deep generative models (VAEs, GANs, diffusion models) or probabilistic modelling is a strong plus.
• You have good programming skills in Python and experience with a deep learning framework such as PyTorch.
• You enjoy interdisciplinary work: you will interact with privacy researchers, legal scholars and energy-sector practitioners.
• You have a good command of spoken and written English.

Prior knowledge of energy systems is not required, we and our consortium partners will provide the domain context.

Additional Information

• We will give you a temporary employment contract (1.0 FTE) of 1.5 years, after which your performance will be evaluated. If the evaluation is positive, your contract will be extended by 2.5 years (4-year contract).
• You will receive a starting salary of €3,204 gross per month based on a 38-hour working week, which will increase to €4,051 in the fourth year ( salary scale P ).
• You will receive an 8% holiday allowance and an 8,3% end-of-year bonus.
• You will receive extra days off. With full-time employment, you can choose between 30 or 41 days of annual leave instead of the statutory 20.

Additional employment conditionsWork and science require good employment practices. This is reflected in Radboud University's primary and secondary employment conditions . You can make arrangements for the best possible work-life balance with flexible working hours, various leave arrangements and working from home. You are also able to compose part of your employment conditions yourself, for example, exchange income for extra leave days and receive a reimbursement for your sports subscription. And of course, we offer a good pension plan. You are given plenty of room and responsibility to develop your talents and realise your ambitions. Therefore, we provide various training and development schemes.

• Which generative modeling approach you would use as a starting point for energy time series on a physical network, why you would choose it, and what you expect the biggest challenge to be. We are interested in your reasoning rather than a particular answer.
• A software application or data analysis project that you are proud of: what it does, what was challenging about it, and what your own contribution was. This may be a personal project, coursework, or work completed for a company. Including a link is optional.
• A one-paragraph description of your MSc thesis, written for a reader outside your field.