PhD Student: AI-Driven 3D XRD Reconstruction

Karlstad University; Grenoble; Sur place; EUR 20 000 - 26 000; Plein temps

Avantages offerts par ce poste

Relocation support

Résumé du poste

The ESRF in Grenoble invites applications for a PhD student position hosted by Université Grenoble Alpes (UGA). You will develop neural-network-driven reconstruction tools for Scanning 3D X-ray Diffraction (S3DXRD) to map orientation and strain fields in crystalline materials.

You will generate synthetic data, train networks, and collaborate with beamline scientists on ID11, ID03 and ESRF’s Algorithms & Data Analysis group, spanning methods development to an open-source release.

Qualifications

• MSc or Master 2 or equivalent 300 ECTS required, eligible for PhD enrollment at UGA.
• Degree in Physics, Materials Science, Engineering, or related field.
• Strong interest in X-ray diffraction and materials characterization.
• Solid background in machine learning.
• Experience with Python and open-source software is a plus.
• Fluent English or proficiency in English.

Responsabilités

• Develop neural-network-driven reconstruction tools for S3DXRD.
• Generate synthetic diffraction training data from simulated microstructures.
• Train neural networks to accelerate reconstruction.
• Validate methods with real ID11 datasets.
• Package and release open-source reconstruction toolkit.

Connaissances

X-ray diffraction

Materials characterization

Machine learning

Python

English proficiency

Independent mindset

Formation

MSc or Master 2 / 300 ECTS

Physics / Materials Science / Engineering

Description du poste

The ESRF in Grenoble invites applications for a PhD student position hosted by Université Grenoble Alpes (UGA). You will develop neural-network-driven reconstruction tools for Scanning 3D X-ray Diffraction (S3DXRD) to map orientation and strain fields in crystalline materials.

You will generate synthetic data, train networks, and collaborate with beamline scientists on ID11, ID03 and ESRF’s Algorithms & Data Analysis group, spanning methods development to an open-source release.