Freie Universität Berlin - Department of Mathematics and Computer Science - Institute of Mathematics
We are currently looking for scientists developing machine learning methods for molecular and material design. Generative models (e.g. variational autoencoders, generative adversarial nets and Markov random fields) are in principle able to address this task, but need to be significantly extended in order to successfully generate complex structures with physical constraints. This project involves work in ECMath project CH19 and WP 1.1 of ERC consolidator grant ScaleCell.
MSc or equivalent in Physics, Computer Science, Mathematics or Engineering.
Desirable: Solid mathematical education, especially computational and numerical methods.; solid knowledge of machine learning theory and methods; extensive experience with software development with Python and a lower-level language (C / C++); experience with machine learning frameworks (e.g. Tensorflow, Theano, PyTorch etc.); publication record in peer-reviewed journals; fluent in written and spoken English.
What we offer:
The research group is highly interdisciplinary, with members from physics, engineering, mathematics, computer science and chemistry. Our aim is to develop fundamental computational methods to solve hard problems in the natural sciences, in particular the molecular sciences (biophysics and theoretical chemistry). We aim at disseminating our methods in high-quality open source software. We conduct research in teams, each team has a bandwidth of theoretical, applied and software-oriented researchers and works on an overarching goal.