Postdoc in Machine Learned Semiconductor: The Computational Nanoelectronics Group at ETH Zurich is seeking a highly motivated post-doctoral fellow to work on the application of machine learning techniques for ab-initio quantum transport simulations. This position focuses on developing methodologies that will help accelerate the characterization of semiconductor devices using state-of-the-art computational techniques.
Postdoc in Machine Learned Semiconductor Material Properties for Quantum Transport Simulations
Designation
Postdoctoral Fellow
Location
ETH Zurich, Zurich, Switzerland
Research Area
Machine Learning, Semiconductor Materials, Quantum Transport Simulations
| Key Details | Information |
|---|---|
| Project Duration | Up to 2 years |
| Project Name | Machine Learning for Optimized Ab-initio Quantum Transport Simulations (MALOQ) |
| Project Start Date | January 1, 2026 |
| Project End Date | December 31, 2029 |
| Team Composition | Collaboration with QuaTrEx developers, two PhD students |
Eligibility/Qualification
- Proven track record in building and deploying machine learning models for applications in materials research.
- Publications in top ML conferences and/or prominent journals related to materials sciences or device physics.
- Strong collaborative skills and desire to work in a friendly research environment.
- Willingness to supervise junior PhD and master’s students.
Job Description
As part of the MALOQ project, the postdoctoral fellow will:
- Train advanced machine learning models to learn atomic, electronic, and vibrational properties of large-scale atomic systems.
- Extend equivariant graph neural networks (GNNs) for Hamiltonian matrix predictions to treat dynamical matrices.
- Compute derivatives for electron-phonon and phonon-phonon coupling elements relevant to quantum transport simulations.
- Engage with multi-GPU codes for efficient training on large, densely-connected graph-structured data.
- Contribute across methodological development, implementation, and application to realistic semiconductor device systems containing thousands of atoms.
- All codes will be made freely available to the scientific community via GitHub.
How to Apply
Interested candidates should submit their applications through the online application portal, which should include:
- CV and list of publications
- Letter of motivation
- Short description of PhD thesis
Please note: Applications via email or postal services will not be considered.
Last Date to Apply
Applications will be accepted until the position is filled, with preference given to early submissions.
For further inquiries, please direct questions to Prof. Dr. Mathieu Luisier at mluisier@iis.ee.ethz.ch (please do not send applications to this address).
Join us at ETH Zurich, where you can make an impact while contributing to cutting-edge research in semiconductor materials and quantum transport simulations!
