Postdoc position on federated learning

**Job Description**
This Postdoc position focuses on addressing the silent pandemic of antimicrobial resistance (AMR) by improving antibiotic discovery. The project aims to effectively prioritize unknown biosynthetic gene clusters and metabolite features for new antimicrobials by predicting structural and functional features from genomic and mass-spectrometric data. A major challenge of scattered proprietary data will be overcome through a federated learning approach. The successful candidate will set up a federated learning infrastructure and develop multimodal machine learning methods to predict connections between mass spectra, biosynthetic gene clusters, molecular structures, and biological activities, in collaboration with national and international partners within the KIC PRIORITY consortium. The research is expected to lead to a new globally accessible infrastructure and algorithms, as well as novel lead compounds.

**Skills & Abilities**
• Affinity with the study of metabolism and analysis of omics data
• Proven proficiency in programming
• Experience with machine learning and, ideally, federated and/or deep learning methods
• Intermediate to high level of statistical and mathematical skills
• Excellent oral and written communication skills in English (C1 level)
• Ambitious, enthusiastic team player and result-driven scientist

**Qualifications**
Required Degree(s) in:
• Bioinformatics
• Computer Science
• Related subject

Note: We’ve analyzed the actual job post using AI, for more details visit the original job post by clicking on “Apply Now”!