PhD student in Autonomous Velocimetry for Fluid Mechanics
Empa, Materials Science and Technology
Dübendorf
Key information
- Publication date:09 December 2025
- Workload:100%
- Contract type:Internship
- Place of work:Dübendorf
Job summary
Join Empa, a leading research institution in materials science. Collaborate in a dynamic, innovative environment.
Tasks
- Develop AI-driven methodologies for experimental fluid mechanics.
- Design multi-fidelity neural networks for adaptive flow reconstruction.
- Integrate frameworks for autonomous measurement and real-time data.
Skills
- MSc in Mechanical or Aerospace Engineering, Physics, or related field.
- Solid programming skills in Python, MATLAB, or C++.
- Strong interest in machine learning, reinforcement learning, and fluid dynamics.
Is this helpful?
Materials science and technology are our passion. With our cutting-edge research, Empa's around 1,100 employees make essential contributions to the well-being of society for a future worth living. Empa is a research institution of the ETH Domain.
PhD student in Autonomous Velocimetry for Fluid Mechanics
The Laboratory for Computational Engineering in Dübendorf is offering a position for two motivated doctoral students.
Your tasks
Optimizing vehicle aerodynamics to reduce transportation emissions, understanding airborne disease transmission, and predicting climate-related transport phenomena all require precise knowledge of fluid flow dynamics. Advanced experimental methods such as Particle Image Velocimetry (PIV) and 3D Lagrangian Particle Tracking (LPT) provide crucial insights. In this project, you will contribute to the development of AI-driven methodologies for experimental fluid mechanics, focusing on:
- Designing multi-fidelity neural networks for adaptive flow reconstruction, enabling both real-time coarse diagnostics and high-fidelity offline velocity field estimation.
- Developing reinforcement learning (RL) algorithms for a multi-agent robotics system that autonomously optimizes 3D velocimetry measurements by dynamically adjusting camera positions and optical parameters.
- Integrating the framework within a digital twin environment for pre-training and simulation-based optimization, enabling autonomous measurement campaigns and real-time data assimilation.
Your profile
We are looking for 2 highly motivated PhD students with a strong analytical background and an MSc degree in Mechanical or Aerospace Engineering, Physics, Computational Science, or a related discipline.
The candidates should have:
- Solid programming skills (Python, MATLAB, or C++).
- Knowledge of the OpenCV library.
- Strong interest in machine learning, reinforcement learning, and fluid dynamics.
- Ability to work independently and collaboratively in an interdisciplinary team.
- Excellent command of English, both written and spoken.
- Experience with experimental fluid mechanics and computer vision is an advantage.
Our offer
We offer a stimulating, multidisciplinary research environment within the ETH Domain, with close collaboration between Empa, ETH Zürich, and other international research partners. Empa provides state-of-the-art experimental and computational infrastructure, internationally competitive employment conditions,and strong support for personal and professional development. The PhD student will be enrolled in the ETH Zürich / University of Zürich doctoral program, depending on academic affiliation. The position is available immediately or upon agreement.
For further information about the position, please contact: E-Mail schreiben, Scientist and Principal Investigator, or E-Mail schreiben, Head of Laboratory for Computational Engineering.
We live a culture of inclusion and respect. We welcome all people who are interested in innovative, sustainable and meaningful activities - that's what counts.
We look forward to receiving your complete online application including a letter of motivation, CV, certificates, diplomas and contact details of two reference persons. Please submit these exclusively via our job portal. Applications by e-mail and by post will not be considered.
