PhD Position (f/m/d) – AI-Based Reactor Design for Critical Resource Extraction

07.04.2026, Academic staff

PhD position at the interface of computational physics, machine learning, and experimental reactor design. The project focuses on developing PINN-based simulations for magnetic particle transport in fluid flows and validating the results through a laboratory-scale reactor. It combines numerical modeling, AI methods, and hands-on experimental work in the context of advanced resource extraction.

We are offering a PhD position at the interface of computational physics, machine learning, and experimental reactor design. The project aims to develop novel approaches for controlling and optimizing the transport of magnetic particles in fluid flows, with applications in advanced resource extraction and separation technologies.

Your Research Project

The project combines data-driven modeling with experimental validation and has two major objectives:

Development of a physics-informed neural network (PINN) framework You will design and implement a simulation framework to model the dynamics of magnetic particles under coupled hydrodynamic and magnetic forces. This includes:

- Particle tracing in complex flow fields

- Integration of magnetic field gradients and magnetophoretic forces

- Exploration of PINNs for forward and inverse problems

Design and realization of an experimental test reactor Based on simulation results, you will develop and build a laboratory-scale reactor to demonstrate and validate the concept. This includes:

- Translation of simulation insights into reactor design

- Experimental investigation of particle retention and transport

- Comparison between model predictions and measured data

Your Profile

We are looking for a motivated and independent candidate with a strong background in physics or engineering. Required qualifications:

- Master’s degree in Physics, Electrical Engineering, or a related discipline

- Solid understanding of fluid dynamics and/or electromagnetism

- Programming experience (preferably Python)

- Interest in machine learning and scientific computing

Desirable skills

- Experience with numerical simulation tools (e.g., COMSOL, CFD frameworks)

- Knowledge of machine learning, especially PINNs or scientific ML

- Experience with particle-based simulations or Monte Carlo methods

- Hands-on experience with experimental work

- Knowledge of the german language is desired but not mandatory

Application process

You should send a motivational statement, a curriculum vitae and copies of degrees and transcripts of study records to PD Dr. habil. Bernhard Gleich (gleich@tum.de) with Matthis Bünning (matthis.buenning@tum.de) in CC. After Initial screening a few prospects will be invited to meet the team in Garching.

The position is suitable for disabled persons. Disabled applicants will be given preference in case of generally equivalent suitability, aptitude and professional performance.

Data Protection Information:
When you apply for a position with the Technical University of Munich (TUM), you are submitting personal information. With regard to personal information, please take note of the Datenschutzhinweise gemäß Art. 13 Datenschutz-Grundverordnung (DSGVO) zur Erhebung und Verarbeitung von personenbezogenen Daten im Rahmen Ihrer Bewerbung. (data protection information on collecting and processing personal data contained in your application in accordance with Art. 13 of the General Data Protection Regulation (GDPR)). By submitting your application, you confirm that you have acknowledged the above data protection information of TUM.

Kontakt: gleich@tum.de, matthis.buenning@tum.de