We are recruiting a PhD student and a Postdoc who want to pursue a scientific career in machine learning method development for biomedicine. We also have open Master thesis projects. Our research focuses on (1) machine learning models of dynamical systems with mechanistic interpretation and feedback from experiments (lab-in-the-loop) and (2) applications in precision medicine and high-throughput biology (single-cell and spatial omics). The successful candidates will be based in the group of David Fischer at the Institute of Artificial Intelligence at the Medical University of Vienna, with ample opportunities to integrate into the national and international research landscape. We are looking for candidates with a background in computational sciences, machine learning, or dynamic systems, and an interest in cell biology or medicine. The pursuit of virtual cells and applied machine learning in biomedicine are gaining significant attention, and we are excited to build momentum around these positions by establishing a dedicated team to address this research focus and by building a network of biomedical collaboration partners.

This position focuses on modeling dynamic systems, specifically inferring homeostatic and dynamic mechanisms from snapshot experiments common in cell biology, such as single-cell and spatial transcriptomics. We aim to build “virtual cells”: computational methods that allow us to simulate how cells in organisms change during disease and treatment. We are particularly excited about applying these machine learning methods to immuno-oncology, infectious disease, autoimmunity, and the engineering of cellular therapeutics. You will contribute creatively and proactively to the development of new mechanistic machine learning methods tailored to cutting-edge omics experiments and their application in biomedicine as part of interdisciplinary teams.

We are seeking individuals who are interested in developing the next generation of mechanistic machine learning methods for biomedicine, with a research focus on reflecting dynamic systems in these models. We aim to overcome challenges in interpretability of black-box models through the usage of large-scale prior knowledge, for example in the shape of networks. Usage of these priors requires candidates to engage with the underlying molecular biology; however, previous experience in biology is not strictly necessary. We are looking for candidates with a background in machine learning, computer science, statistics, physics, bioinformatics, systems biology or similar fields. Candidates with a background in biology or medicine are also eligible if they possess strong quantitative skills and experience in machine learning.

Interested, but not a perfect fit for this specific position? Contact us to explore other opportunities for collaboration!

See job ad below.