The Division of Computational Pharmacy, Department of Pharmaceutical Sciences, is offering a PostDoc position to develop and apply cutting-edge computational methodology integrating physicochemical knowledge into deep neural network algorithms for drug discovery applications. The project will focus on the efficient and accurate sampling of protein-ligand conformational states, i.e. protein-ligand co-folding. The position is funded by a grant from the Novartis Forschungsstiftung.
Your assignments
The PostDoc position is available to extend ongoing research on the development of novel algorithms for drug design combining physics-based modeling with deep neural network concepts. You will be responsible for the development and implementation of novel deep neural network models based on recent developments in diffusion models and GFlowNets.
Minimum Requirements:
* PhD in the fields of Physics, Physical / Computational Chemistry, Mathematics or Computer Sciences
* Strong experience in developing and applying deep neural network concepts
* Knowledge in generative models, e.g. diffusion models, is desirable
* Fluent verbal and written communication skills in English
* Highly motivated, interactive team player
Additional Information:
* Opportunity to work with and develop emerging technologies in the field of Computational Drug Design
* International and collaborative research environment
* Possibility to increase your academic profile and supervise junior researchers
#J-18808-Ljbffr