Postdoctoral Researcher in Machine Learned Semiconductor Material Properties for Quantum Transport Simulations / Postdoctoral Researcheress in Machine Learned Semiconductor Material Properties for Quantum Transport Simulations

Postdoc in Machine Learned Semiconductor Material Properties for Quantum Transport Simulations

100%, Zurich, fixed-term

The simulation of electronic devices has a long and successful history of accompanying experimental developments, whether in transistors or memory cells. To maintain practical relevance, such Technology Computer Aided Design (TCAD) tools must operate at the ab-initio and quantum mechanical levels. Moreover, they should capture the interplay between electrical (voltage-induced currents), thermal (excitation of crystal vibrations), and structural (migration of atoms) effects with atomic-level resolution. This can be achieved by self-consistently coupling 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 begun implementing a novel TCAD tool named QuaTrEx, which is capable of performing ab-initio QT calculations at an unprecedented scale. Since QuaTrEx aims to solve for the transport and interactions of various quanta (such as electrons and phonons) directly at atomic resolution, it necessitates ab-initio material inputs corresponding to the simulated device components, including the Hamiltonian and Dynamical matrices, electron-phonon coupling elements, forces, and energies. The computation of these inputs for device-scale structures using methods like DFT currently poses a significant challenge.

Project Background

The Computational Nanoelectronics Group was awarded a grant from the Swiss National Science Foundation for the 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 objective 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. In this context, we are seeking a post-doctoral fellow to join a team that also includes two PhD students and will work closely with the developers of QuaTrEx.

Job Description

As part of the MALOQ project, your responsibilities will include training state-of-the-art ML models to learn atomic, electronic, and vibrational properties of large-scale atomic systems that represent the basic building blocks of semiconductor devices. The goal is to predict these properties for arbitrarily large structures, achieving DFT-level accuracy.

Initially, you will extend our large-scale equivariant GNNs developed for Hamiltonian matrix prediction to encompass dynamical matrices. This ML framework will enable us to produce the derivatives of both quantities, which correspond to the electron-phonon and anharmonic phonon-phonon coupling elements. With these, we can compute dedicated scattering rates for use in quantum transport simulations. Ultimately, we aim to pre-train a common GNN backbone model capable of predicting electronic, structural, and thermal quantities while leveraging underlying symmetries for enhanced computational efficiency. A significant computational aspect will involve deploying multi-GPU codes to effectively train on the large, densely-connected, graph-structured data present in our systems of interest.

Your contributions will span methodological development, implementation, and application to practical semiconductor device systems composed of thousands of atoms. All developed codes will be made freely available to the scientific community through GitHub.

Profile

• A proven track record in building and deploying ML models for applications in materials research, coupled with a willingness to engage in both methods development and practical applications.
• Publications in top ML conferences and/or prominent journals related to materials science and device physics.
• A collaborative spirit with a penchant for working in a friendly research environment.
• Acommitment to supervising junior PhD and master's students.

Workplace

You will be part of ETH Zurich, a leading university that not only supports your professional development but also contributes positively to society through research and education.

We Offer

• A meaningful role at ETH Zurich that supports your professional growth while making a positive social impact.
• Numerous benefits, including public transport season tickets, car-sharing opportunities, a wide range of sports offered by the ASVZ, childcare, and attractive pension plans.
• An exciting and challenging position within a highly motivated team of physicists, electrical engineers, and computer scientists, with a salary aligned with ETH Zurich's standards for postdoctoral researchers.
• Please note that the duration of the postdoc can be up to two years, and participation in international conferences, as well as collaboration with industry and academia, is highly encouraged and supported.

We Value Diversity and Sustainability

In alignment with our values, ETH Zurich advocates for an inclusive culture that promotes equal opportunities and values diversity. We nurture a working and learning environment where the rights and dignity of all staff and students are respected. Sustainability is fundamental to us, and we continually strive towards a climate-neutral future.

Curious? So Are We.

If you're interested in this opportunity, apply online using the form below. Please ensure that your submission includes the following documents:

• CV and list of publications
• Letter of motivation
• Short description of your PhD thesis

Only applications matching the job profile will be considered. For further information about the Computational Nanoelectronics Group, please visit our website. Inquiries regarding the position can be directed to Prof. Dr. Mathieu Luisier at mluisier@iis.ee.ethz.ch (note: no applications).

About ETH Zurich

ETH Zurich is one of the world’s leading universities specializing in science and technology. We are renowned for our excellent education, cutting-edge fundamental research, and direct transfer of new knowledge into society. Over 30,000 individuals from more than 120 countries find ETH Zurich to be a place that fosters independent thinking and inspires excellence. Situated in the heart of Europe, we forge connections worldwide to develop solutions for today’s and tomorrow’s global challenges.