Postdoc position in Bayesian Uncertainty Quantification and Machine Learning

In der aktuellen Covid-19 Situation laufen die Rekrutierungen weiter. Es kann dabei allerdings zu Verzögerungen kommen. Vielen Dank für Ihr Verständnis.

100%, Zurich, fixed-term

The Computational Science and Engineering Lab (CSElab) at ETH Zürich is looking for a postdoc working on Bayesian uncertainty quantification (BUQ) on multi-scale computational models.

The research of the CSElab at ETH Zürich, headed by Prof. Dr. Petros Koumoutsakos, focuses on the development of high-performance computational tools for the study of complex scientific and engineering problems. Our main research areas are: uncertainty quantification of large scale computational models, machine learning algorithms for the prediction and control of complex dynamical systems, multi-scale modeling involving molecular dynamics, particle methods and macro-scale differential equation models.

Project background

This position is part of the project Data Driven Computational Mechanics at Exascale (DCoMEX), funded by Horizon 2020. It is a joint project with the National Technical University of Athens (NTUA), the University of Cyprus (UC) and the Technical University of Munich (TUM).

The project aims to provide advances to the field of computational mechanics by developing novel numerical methods enhanced by artificial intelligence algorithms that are deployed with scalable software to exascale computing architectures. Our methods fuse machine learning with efficient numerical methods and incorporate experimental data at multiple levels of fidelity to quantify model uncertainties. Efficient deployment of these methods in exascale computing architectures will provide scientists and engineers with unprecedented capabilities for predictive simulations of mechanical systems in applications ranging from bioengineering to manufacturing.
The methodology will be demonstrated in two case studies:

• patient-specific optimisation of cancer immunotherapy treatment
• design of advanced composite materials and structures at multiple scales

Job description

Part of your job will be to design Bayesian models in order to infer the parameters of multi-scale computational models. In addition, efficient algorithms for the sampling of the posterior distribution in Bayesian problems should be developed. You will work closely with scientists at NTUA and jointly develop the statistical and computational models for mechanical structures at multiple scales. You will deploy the statistical models and sampling algorithms in Korali, a high-performance computational framework for BUQ, optimization and ML, that has been developed in our lab. In this part you will collaborate with software engineers and statisticians in our lab. Finally, you will have an active role in the cancer immunotherapy and design of advanced composite materials applications. You will work in an interdisciplinary environment (from UC and TUM) in order to insert Korali in the workflow of each application.

We offer you a full-time position, starting upon agreement with the earliest starting of 1 november 2021. You will work in an interdisciplinary team of researchers with in-depth experience in BUQ, statistical modelling, ML, sampling and optimization algorithms.

Your profile

We are looking for a proactive and motivated candidate who meets the requirements for a postdoc at ETH Zurich and has a university degree in Computational Science, Computer Science, Applied Mathematics, Engineering or Physics with a doctorate from a recognized University. You should have experience in Bayesian uncertainty quantification, machine learning and high-performance computing. Good knowledge of C++ is required. Expertise in mathematical modeling with partial differential equations (PDEs), numerical solution of PDEs and stochastic optimization methods is highly appreciated. You must be highly motivated to learn and apply statistical modeling and sampling techniques, and work in a dynamic environment with other doctoral students and postdocs. The ability to work independently and excellent communication skills in English (both written and spoken) completes your profile.

ETH Zurich

ETH Zurich is one of the world’s leading universities specialising 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 people from more than 120 countries find our university to be a place that promotes independent thinking and an environment that inspires excellence. Located in the heart of Europe, yet forging connections all over the world, we work together to develop solutions for the global challenges of today and tomorrow.

Working, teaching and research at ETH Zurich