The Digital Chemistry Laboratory is led by Prof. Dr. Kjell Jorner at the Institute of Chemical and Bioengineering, within the Department of Chemistry and Applied Biosciences at ETH Zurich and associated with the ETH AI Center. We are an interdisciplinary group at the intersection of chemistry and computer science. Our mission is to accelerate chemical discovery using digital tools. We predict chemical reactivity and molecular properties using machine learning, artificial intelligence, computational chemistry, and cheminformatics. Our ultimate goal is the computer-aided design of molecules and catalysts.
Project background
Machine learning potentials (MLPs) that predict the energy of molecules or materials from their three-dimensional atomic coordinates are increasingly replacing quantum-chemical simulations in high-throughput screening and dynamical simulations. Trained on large amounts of chemical data, such MLPs can serve as āfoundation modelsā that are broadly applicable across chemical and configurational space. While significant progress has been made in developing MLPs for equilibrium structures, they have been less succesful for chemical reactions, for which much less data is available. While efforts are underway for data collection and training of reactive MLPs, another approach is to augment the architecture of the MLPs to better accommodate reactive events. In this project, we will develop and validate such MLPs that borrow elements from classical reactive force fields. These reactive MLPs target a broader generalization performance and will require much less training data. Finally, we will employ the developed MLPs for reaction prediction in important reaction classes.
Job description
As a postdoc in our growing team, you will develop and validate machine learning potentials based on reaction data. You will also work with and adapt classical reactive force fields for integration into the MLPs. Finally, you will validate the methods on important chemical reactions. Besides your own main project focus, you will contribute to the supervision of PhD and undergraduate students in the group.
Profile
We are looking for a committed and motivated candidate that is excited to push the boundaries of research in digital chemistry.
Essential experience, skills, and characteristics:
- A PhD in either chemistry, chemical engineering, computational science, materials science, physics, or related fields, or expectation of obtaining such a degree before February 2025
- English proficiency
- Self-motivation, ability to work independently and solution-oriented mentality
- Interdisciplinary and collaborative mindset and desire to work with people from different disciplines and backgrounds
- Programming experience using languages such as Julia, Python, R, etc.
Desirable criteria:
- Experience of machine learning potential development
- Experience of classical force field development
- Experience of reaction simulations
For more information and to apply visit https://jobs.ethz.ch/job/view/JOPG_ethz_Z5i1KZ46adYaXSutfY