The simulation of electronic devices has a long and successful history of accompanying experimental developments, whether for transistors or memory cells. Today, in order to remain practically relevant, such technology computer-aided design (TCAD) tools must operate at the ab-initio and quantum mechanical levels. Furthermore, these tools should capture the interplay between electrical (voltage-induced currents), thermal (excitation of crystal vibrations), and structural (migration of atoms) effects with atomic resolution. Achieving this requires self-consistent coupling of molecular dynamics (MD), density-functional theory (DFT), and quantum transport (QT) simulations for both electrons and phonons.
The Computational Nanoelectronics Group at ETH Zurich has recently initiated the development of a cutting-edge TCAD tool named QuaTrEx, capable of performing ab-initio QT calculations at an unprecedented scale. QuaTrEx aims to solve for the transport and interactions of various quanta (electrons, phonons, etc.) directly at atomic resolution, necessitating ab-initio material inputs that correspond to the simulated device components, including the Hamiltonian and dynamical matrices, electron-phonon coupling elements, forces, and energies. Currently, computing these inputs for device-scale structures using methods such as DFT presents a bottleneck in the application’s capabilities.
Recently, the Computational Nanoelectronics Group was awarded a grant from the Swiss National Science Foundation entitled “Machine Learning for Optimized Ab-initio Quantum Transport Simulations” (MALOQ). The project officially commenced on January 1st, 2026, and will conclude on December 31st, 2029. The primary goal of this research initiative is to leverage machine learning (ML) techniques, particularly (equivariant) graph neural networks, to accelerate the generation of all physical quantities required for ab-initio QT simulations of nanoelectronic devices. In this context, we are seeking a post-doctoral fellow who will join a team that includes two PhD students and will closely collaborate with the developers of QuaTrEx.
As part of the MALOQ project, you will train state-of-the-art ML models to ascertain atomic, electronic, and vibrational properties of large-scale atomic systems that represent the foundational elements of semiconductor devices. The objective is to predict these properties for arbitrarily large structures with DFT-level accuracy.
Your initial focus will be on extending large-scale equivariant graph neural networks (GNNs) developed for Hamiltonian matrix prediction to address dynamical matrices. This ML framework will also enable us to produce the necessary derivatives of both quantities, which correspond to electron-phonon and anharmonic phonon-phonon coupling elements. These derivatives will subsequently facilitate the computation of dedicated scattering rates, which will be integrated into quantum transport simulations. In the long term, we aspire to pre-train a unified GNN backbone model capable of predicting electronic, structural, and thermal quantities, efficiently utilizing underlying symmetries for computational effectiveness. A significant computational aspect will involve deploying multi-GPU codes to proficiently train on the large, densely connected, and graph-structured data pertinent to our research interests.
Your contributions will span methodological development, implementation, and application to realistic semiconductor device systems comprising thousands of atoms. All developed codes will be freely available to the scientific community via GitHub.
You will be immersed in a vibrant research atmosphere at ETH Zurich, engaged with highly motivated physicists, electrical engineers, and computer scientists.
Aligned with our core values, ETH Zurich fosters an inclusive culture. We promote equal opportunity, value diversity, and nurture a working and learning environment that respects the rights and dignity of all our staff and students. Visit our Equal Opportunities and Diversity website to learn how we ensure a fair and open atmosphere that allows everyone to thrive. Sustainability is a fundamental principle for us, and we are consistently working toward a climate-neutral future.
We look forward to receiving your online application using the form below.
ETH Zurich is one of the world’s leading universities specializing in science and technology. Renowned for excellent education, pioneering research, and the direct transfer of new knowledge to society, ETH Zurich hosts over 30,000 individuals from more than 120 countries who find our university a place that promotes independent thinking and inspires excellence. Situated in the heart of Europe while forging global connections, we collaborate to address today's and tomorrow's challenges.
Location : Zürich
Country : Switzerland