Research Scientist in Scientific AI and Geotechnical Engineering

Shaping the Future of Scientific AI in Geotechnical Engineering

The Chair of Geotechnical Engineering at ETH Zurich, part of the Institute for Geotechnical Engineering (IGT), focuses its teaching and research on foundation engineering, soil mechanics, and natural hazards. Our objective is to combine theoretical knowledge with experiments and numerical simulations to develop new methods for understanding and predicting the behaviour of soils, foundations, and infrastructure.

We are seeking an intellectually curious scientist or engineer to join our research group. The role focuses on developing and integrating modern Artificial Intelligence (AI) methods into geotechnical engineering research while maintaining a strong connection to the underlying physics and mechanics. The goal is not to replace physics-based engineering with purely data-driven AI, but to use AI to transform the way research is performed—from numerical model generation and experimental data acquisition to analysis, visualization, and communication.

This position combines scientific research, computational engineering, research automation, data science, and the development of reusable AI-enabled tools. A central objective is to identify new opportunities where AI can enable research that would otherwise be difficult or impossible, and to develop capabilities that can be used across the entire group.

Key Responsibilities

• Scientific AI and Physics-Informed Modelling: Develop and apply AI and machine-learning approaches to challenging problems in geotechnical engineering and computational mechanics, emphasizing approaches that combine data with physical knowledge. Explore topics including physics-informed machine learning, hybrid constitutive modelling, surrogate models, inverse problems, uncertainty quantification, and AI-assisted scientific discovery applied to soil behaviour, liquefaction, and infrastructure resilience.
• AI-Enabled Numerical Modelling: Develop tools for automating and accelerating numerical modelling workflows, including finite element (FE), discrete element (DEM), and material point method (MPM) simulations. Automate tasks such as model generation, mesh creation, parameter studies, high-performance computing (HPC) execution, and standardised post-processing to create robust, reusable tools for the research group.
• Automation of Experimental Research: Develop AI-enabled methods for the acquisition, processing, and interpretation of experimental data from laboratory and centrifuge testing. Automate sensor-data processing, synchronization of measurement systems, computer-vision analysis, and the extraction of deformation and failure mechanisms from images and videos.
• Geotechnical Data Intelligence: Develop methods to exploit the growing volume of geotechnical data available within the group and through external repositories. Organize and extract information from historical experiments and numerical analyses, and contribute to the development of structured, physics-aware geotechnical datasets to support parameter inference and model calibration.
• Scientific Visualisation and Communication: Develop automated approaches for transforming research results into high-quality visualisations, animations, and videos. Create tools that support scientific publications, presentations, and effective communication of research through various platforms.
• Group-Wide AI Capability: Help establish AI as a broadly accessible research capability within the group. Identify opportunities for AI across ongoing research activities, develop common tools and workflows, provide internal training and documentation, and work directly with researchers to enable them to use modern AI and computational methods effectively.

Profile and Qualifications

We are looking for a candidate who combines strong computational skills with an interest in physical systems and engineering research. A background in geotechnical engineering is not mandatory but can represent an advantage. Candidates from other fields with strong expertise in computational mechanics and Scientific AI are strongly encouraged to apply.

• PhD in computational mechanics, computational engineering, scientific machine learning, applied mathematics, computer science, civil or mechanical engineering, or a closely related discipline.
• Excellent programming skills and a strong background in numerical methods, such as FEM, FD, DEM, or MPM.
• Demonstrated experience with machine learning, modern AI methods, and AI-assisted software development.
• Experience with scientific data engineering, databases, and the processing of large or heterogeneous datasets.
• Experience with HPC, parallel computing, and/or GPU computing.
• Experience with automated simulation workflows and APIs.
• Experience with scientific visualisation and the automated generation of figures, animations, or videos.
• Experience with computer vision and image/video analysis is particularly valuable.

Beyond specific technical qualifications, we value scientific creativity, strong software-development practices, independence, collaborative ability, and an enthusiasm for learning new areas. The successful candidate should be able to understand an engineering or scientific problem, identify where AI or computational methods can provide genuine added value, develop a rigorous solution, and transform that solution into a reusable capability for other researchers.

What We Offer

• The opportunity to help shape a new research direction at the intersection of Artificial Intelligence, computational mechanics, experimentation, and geotechnical engineering.
• Considerable freedom to identify research opportunities and contribute to the development of new methods as AI technologies and Scientific AI continue to evolve.
• The opportunity to work across scientific research, computational engineering, numerical simulations, experimental research, and data science.
• Close collaboration with PhD students, postdoctoral researchers, and senior scientists in an interdisciplinary research environment.
• The opportunity to develop reusable AI-enabled tools and workflows that strengthen research capabilities across the group.