PhD Student (m/w/d)

Helmholtz-Zentrum hereon GmbH; Geesthacht; On-site; EUR 40,000 - 60,000; Full time

Job summary

Helmholtz-Zentrum Hereon's Institute of Material and Process Design seeks a PhD candidate to develop a physics-guided digital twin for magnesium alloys. You will integrate experiments, crystal plasticity, and ML to predict microstructure evolution and properties under varying processing conditions.

Collaborating across disciplines, you will implement Python-based workflows (PyTorch, Scikit-Learn) and contribute to ICME framework development, bridging data-driven models with mechanistic

Qualifications

• PhD in computational materials engineering, machine learning, and digital twins.
• Experience with crystal plasticity, phase-field modeling, precipitation, and ML.
• Proficiency in Python and ML frameworks for workflows.

Responsibilities

• development of physics-guided machine-learning models for composition-process-structure-property relationships in magnesium alloys
• combination of crystal plasticity, phase-field, precipitation, and machine-learning approaches into a unified digital twin framework
• implementation of simulation and machine-learning workflows in Python (e.g. PyTorch, Scikit-Learn, etc.)
• incorporation of experimental microstructure and texture characterization data obtained from optical microscopy, SEM, EBSD, XRD, and mechanical testing
• investigation of uncertainty quantification and explainable artificial intelligence methods (XAI) for materials modeling
• validation of computational predictions in collaboration with experimental and modeling researchers

Skills

Physics-guided ML

Crystal plasticity

Machine learning

Team collaboration

Education

PhD in Materials Science or related field

Tools

Python

PyTorch

Scikit-Learn

Phase-field modeling

Crystal plasticity

Job description

Helmholtz-Zentrum Hereon

The Helmholtz-Zentrum Hereon conducts cutting-edge international research for a changing world: Around 1,000 employees contribute to the tackling of climate change, the sustainable use of the world's coastal systems and the resource-compatible enhancement of the quality of life. From fundamental research to practical applications, the interdisciplinary research spectrum covers a unique range.

Institute of Material and Process Design

The Institute of Material and Process Design is dedicated to the sustainable and ecological development of innovative materials and manufacturing processes, especially for the transportation sector and medical technology. To this end, materials are tailored and manufacturing processes are designed to conserve resources - from the modeling of material behavior to the development of the material to the finished component.

PhD position on Physics-Guided Digital Twin Development for Composition-Process-Structure-Property Modeling of Magnesium Alloys

Reference code: 1057 - 2026/WD 1

Commencement date: as soon as possible

Work location: Geesthacht

Application deadline: November 12th, 2026

The Institute of Material and Process Design at the Helmholtz-Zentrum Hereon is offering a 4-year PhD position in the field of computational materials engineering, machine learning, and digital twins for advanced lightweight materials. The focus of the PhD project will be the development of a physics-guided digital twin framework for magnesium alloys by integrating experimental characterization, crystal plasticity, phase-field modeling, precipitation modeling, and machine learning approaches to establish quantitative composition-process-structure-property relationships. Building upon recently developed machine-learning approaches for structure-property prediction in extruded magnesium alloys, the project aims to advance toward a next-generation Integrated Computational Materials Engineering (ICME) framework capable of predicting microstructure evolution and resulting mechanical properties across previously unseen processing conditions and material states.

The candidate will work closely with interdisciplinary teams combining expertise in magnesium alloy development, thermomechanical processing, crystal plasticity, phase-field modeling, machine learning, and advanced experimental characterization.

The objective of the project is to bridge the gap between purely data-driven materials modeling and mechanistic microstructure simulations by combining crystal plasticity, dynamic recrystallization, precipitation kinetics, and machine learning into a unified digital-twin framework. The resulting methodologies shall enable accelerated alloy and process design by leveraging experimentally validated physics-guided surrogate models with improved extrapolation capabilities beyond the limits of conventional machine-learning approaches. This work directly contributes to the digital transformation of materials development and manufacturing technologies for future lightweight engineering applications.

Equal opportunity is an important part of our personnel policy.

We would therefore strongly encourage qualified women to apply for the position.

• development of physics-guided machine-learning models for composition-process-structure-property relationships in magnesium alloys
• combination of crystal plasticity, phase-field, precipitation, and machine-learning approaches into a unified digital twin framework
• implementation of simulation and machine-learning workflows in Python (e.g. PyTorch, Scikit-Learn, etc.)
• incorporation of experimental microstructure and texture characterization data obtained from optical microscopy, SEM, EBSD, XRD, and mechanical testing
• investigation of uncertainty quantification and explainable artificial intelligence methods (XAI) for materials modeling
• validation of computational predictions in collaboration with experimental and modeling researchers
• publication an...