100%, Zurich, fixed-term
The simulation of electronic devices has a long and successful history of accompanying experimental advancements, whether for transistors or memory cells. Today, to be practically relevant, such technology computer-aided design (TCAD) tools must operate at the ab-initio and quantum mechanical levels. They should also capture the interplay between electrical (voltage-induced currents), thermal (excitation of crystal vibrations), and structural (migration of atoms) effects with atomic resolution. This can be achieved by self-consistently coupling molecular dynamics (MD), density-functional theory (DFT), and quantum transport (QT) simulations of both electrons and phonons.
The Computational Nanoelectronics Group at ETH Zurich has recently initiated the implementation of a new, state-of-the-art TCAD tool called QuaTrEx, which is capable of performing ab-initio QT calculations at an unprecedented scale. As QuaTrEx aims to solve for the transport and interactions of various quanta (electrons, phonons, etc.) directly at atomic resolution, it requires ab-initio material inputs corresponding to the simulated device components, such as Hamiltonian and dynamical matrices, electron-phonon coupling elements, forces, and energies. Computing these inputs for device-scale structures using methods like DFT currently poses a bottleneck in the tool's capabilities.
The Computational Nanoelectronics Group has been awarded a grant from the Swiss National Science Foundation for a project titled Machine Learning for Optimized Ab-initio Quantum Transport Simulations (MALOQ), which officially commenced on January 1st, 2026, and will conclude on December 31st, 2029. The goal of this research initiative is to apply machine learning (ML) techniques, particularly (equivariant) graph neural networks, to accelerate the creation of all physical quantities necessary for ab-initio QT simulations of nanoelectronic devices. We are seeking a post-doctoral fellow to join our team, which includes two PhD students, and to collaborate closely with the QuaTrEx developers.
As part of the MALOQ project, you will train state-of-the-art ML models to learn atomic, electronic, and vibrational properties of large-scale atomic systems representing the building blocks of semiconductor devices. The aim is to predict these properties for arbitrarily large structures, maintaining a DFT-level of accuracy.
Your initial focus will be to extend the large-scale equivariant GNNs we develop for Hamiltonian matrix prediction to also address dynamical matrices. This ML framework will enable us to produce the derivatives of both quantities, corresponding to electron-phonon and anharmonic phonon-phonon coupling elements. Using these derivatives, dedicated scattering rates can be computed for future quantum transport simulations. Ultimately, our goal is to pre-train a common GNN backbone model capable of predicting electronic, structural, and thermal quantities while leveraging underlying symmetries for enhanced computational efficiency. You will have a significant computational component, deploying multi-GPU codes to efficiently train on the large, densely connected, and graph-structured datasets characteristic of our systems.
Your contributions will span methodological development, implementation, and application to realistic semiconductor device systems consisting of thousands of atoms. All codes developed will be made freely available to the scientific community via GitHub.
At ETH Zurich, we provide a dynamic work environment that fosters professional development and contributes positively to society. You can expect numerous benefits including public transport season tickets, car-sharing options, a wide range of sports offered by the ASVZ, childcare provisions, and attractive pension benefits. We offer an exciting and challenging opportunity within a highly motivated team of physicists, electrical engineers, and computer scientists, along with a competitive salary in line with ETH Zurich’s standards for post-doctoral positions. The duration of the postdoc can be up to two years, with encouragement and support for participation in international conferences and collaborations with industry and academia.
ETH Zurich is committed to promoting an inclusive culture that encourages equality of opportunity. We value diversity and strive to foster a working and learning environment that respects the rights and dignity of all staff and students. Sustainability is a core principle for us, and we continue to work towards a climate-neutral future.
We look forward to receiving your online application using the form below. Applications will be considered only if they match the job profile.
If you have any questions regarding this position, please contact Prof. Dr. Mathieu Luisier at mluisier@iis.ee.ethz.ch (please note, no applications are accepted via email).
ETH Zurich is one of the world’s leading universities specializing in science and technology. We are renowned for our exceptional education, groundbreaking fundamental research, and direct application of new knowledge to societal challenges. More than 30,000 people from over 120 countries find ETH Zurich to be a place that promotes independent thinking and inspires excellence. Located in the heart of Europe, we develop collaborative solutions for the global challenges facing us today and in the future.
Location : Zürich
Country : Switzerland