PhD Student in Electronic-Structure Machine Learning for Materials Paul Scherrer Institute (PSI) in Switzerland

The Paul Scherrer Institute (PSI) in Switzerland is offering a PhD position in Electronic-Structure Machine Learning for Materials. PSI is the largest research institute for natural and engineering sciences in Switzerland, renowned for its interdisciplinary research in future technologies, energy, climate, health innovation, and fundamental science. This PhD project is part of the Swiss initiative 'Learning the electrons: Design, training and application of a general model of the electronic structure of matter', which aims to develop next-generation machine-learning models for electronic-structure theory.

The project leverages recent advances in machine-learned interatomic potentials and electronic-structure simulations to create scalable models capable of predicting advanced electronic properties of materials with high accuracy and efficiency. It combines machine learning, quantum-mechanical simulations, and scientific software infrastructure, and is jointly led by Dr Giovanni Pizzi (PSI) and Prof Dr Michele Ceriotti (EPFL). The research focuses on developing and applying machine-learning approaches that explicitly represent the electronic structure of materials, enabling predictions beyond standard interatomic potentials.

As a PhD student, you will contribute to the co-development of transferable electronic-ML (e-ML) models, investigating model design, training strategies, computational efficiency, transferability, and predictive accuracy across diverse materials systems. You will generate and curate high-quality electronic-structure datasets using automated AiiDA-based workflows, validate and benchmark model performance for advanced materials properties (including electron–phonon coupling, Berry phases, and other electronic-structure quantities), and explore the development of foundation models for materials applicable across the periodic table. The role also involves contributing to robust, reusable, and efficient open-source software and integrating machine-learning frameworks with established electronic-structure codes.

Applicants should have a Master's degree (or be close to completion) in physics, materials science, chemistry, engineering, or a related field. Hands-on experience with density functional theory (DFT) and/or machine-learning models applied to materials is required, along with working knowledge of Python for scientific computing and data analysis. Strong communication skills in English and an interest in quantum simulations, modern ML models, computational methods, and materials modeling are essential. The PhD will be based at PSI in the Materials Software and Data group of Dr Giovanni Pizzi, with close collaboration with Prof Dr Michele Ceriotti's group at EPFL. Enrollment in the doctoral program in Materials Science and Engineering (EDMX) at EPFL is included, with coursework and possible teaching duties. Research results are expected to be published in peer-reviewed journals and presented at international conferences.

PSI offers an interdisciplinary, innovative, and dynamic research environment, systematic training on the job, personal development opportunities, and modern employment conditions. Diversity is highly valued, and applications from under-represented groups are encouraged. For further information, contact Dr Giovanni Pizzi at [email protected].

To apply, submit your application online by 21 June 2026, including a cover letter, CV, transcript of records, and contact details for two referees. The application portal is available at this link. For more information about PSI, visit www.psi.ch.