Professorship of Data-driven Materials Modeling

Ph.D. Position on Physics-informed Probabilistic Learning for Mechanics and Materials (m/w/d)

29.10.2026, Academic staff

A PhD position is available in Physics-informed Probabilistic Learning for Mechanics and Materials. The successful candidate will work at the interface of computational mechanics, materials modeling, uncertainty quantification, and probabilistic machine learning.

The successful candidate will work at the interface of computational mechanics, materials modeling, uncertainty quantification, and probabilistic machine learning. The research targets open problems in the predictive modeling of engineering materials: how does microstructure dictate macroscopic mechanical and functional behavior, how can constitutive models be learned and calibrated from limited and noisy experimental data, how can we quantify and propagate uncertainty through high-dimensional, multiscale models, and how can we design materials and components whose performance is robust to manufacturing variability? Answering these questions requires methods that go well beyond standard machine learning, embedding physical laws, thermodynamic consistency, symmetries, and probabilistic reasoning directly into the learning framework.
Research is motivated by concrete applications, including additively manufactured and architected materials (metamaterials), composite materials, porous media and geomaterials, and soft/biological tissues.

Please follow the link below for additional information and the application process.

Kontakt: contmech@mw.tum.de