Postdoctoral Fellow - Machine learning for decoding cellular networks

 
  • EMBL
  • Germany
  • Jun 21, 2021
Science Full Time - Fixed Term

Job Description:

The research groups of Oliver Stegle and Lars Steinmetz look for a computational postdoctoral fellow to join an ambitious collaborative project with the goal to decipher molecular networks by integrating AI-based analytics and causal inference with large-scale functional genomics screens.    Our research groups combine internationally leading excellence in genomics technology (Steinmetz) with computational innovations in multi-omics integration, causal inference and machine learning (Stegle). The fellow will work in a highly multidisciplinary setting between both laboratories and industrial partners, funded by a project grant from the EMBL-GSK alliance. The aim of this project is driving new strategies for causal inference from high-throughput single-cell perturbation readouts. A unique innovative angle will be to directly couple model outputs with experimental decisions, thereby achieving data driven and adaptive experimental design. Recent publications of the Stegle & Steinmetz research groups:

You will work in a team together with experimentalists and other computational scientists to develop tailored machine learning and causal inference methodologies that are designed to fully exploit data from high-throughput perturbation screens. In addition to the development of novel methods, it is also your responsibility to direct the experimental activities, both to validate putative causal relationships to use model outputs for adaptive, information-efficient data acquisition.  

The successful applicant will hold a doctoral degree or equivalent qualification in computer science, statistics, mathematics, physics, and/or engineering, or a degree in biological science with demonstrated experience in computational and statistical development. Previous experience in developing and applying statistical and machine-learning based methods to large real world datasets is expected. Expertise in analysis of omics data, genetics, statistical interpretation and analysis of next-generation sequencing datasets is beneficial, as is communicating results in scientific conferences and papers. We look for a highly motivated, creative, organized, and well-positioned team member to lead this scientific project at all stages.



Why not! Well, EMBL is an inclusive, equal opportunity employer offering attractive conditions and benefits appropriate to an international research organisation with a very collegial and family friendly working environment. The remuneration package comprises from a competitive salary, a comprehensive pension scheme, medical, educational and other social benefits, as well as financial support for relocation and installation, including your family and the availability of an excellent child care facility on campus. The Steinmetz Lab works across two sites at EMBL Heidelberg and Stanford University and is one of the world’s leading labs in technology development for functional genomics, by combining experimental work and bioinformatics. The Stegle lab works across EMBL-Heidelberg and the German Cancer Research Center and is one of the world’s leading labs in machine learning and computational genomics.

We are Europe’s flagship research laboratory for the life sciences – an intergovernmental organisation performing scientific research in disciplines including molecular biology, physics, chemistry and computer science. We are an international, innovative and interdisciplinary laboratory with more than 1600 employees from many nations, operating across six sites, in Heidelberg (HQ), Barcelona, Hinxton near Cambridge, Hamburg, Grenoble and Rome.

Our mission is to offer vital services in training scientists, students and visitors at all levels; to develop new instruments and methods in the life sciences and actively engage in technology transfer activities, and to integrate European life science research.

Please note that appointments on fixed term contracts can be renewed, depending on circumstances at the time of the review.