PhD Position - Machine Learning & Genomics in Antimicrobial Resistance Diagnostics

• Development and clinical evaluation of machine-learning models for the detection of resistance plasmids directly from routine MALDI-TOF mass spectra
• Genomic analysis of carbapenemase-producing Enterobacterales and their mobile genetic elements, using short- and long-read whole genome sequencing
• Establishment and analysis of linked MALDI-TOF and genome datasets as the basis for generalizable predictive models
• Experimental validation of computational predictions through conjugation, plasmid curing and stability assays, supported by a dedicated technical assistant
• Contribution to national and international consortia (DZIF TTU-HAI, ESGEM-AMR) and presentation of results at conferences and in peer-reviewed journals

• Completed Master's degree in bioinformatics, microbiology, or a comparable subject
• Confident programming in Python and experience working in a Linux environment with bioinformatics tools
• Practical experience with machine learning and/or analysis of whole-genome sequencing data
• Interest in bacterial genomics and clinical microbiology and willingness to combine computational work with experiments at the bench
• Independent and structured working style, team orientation and scientific rigour, ideally evidenced by a first publication

You will join a newly established research group as one of its first members, with close supervision, technical support, and scope to shape your research environment, while benefiting from regular exchange with CMFI and participation in IGIM.

Newly established research group at the interface of medical microbiology, bacterial genomics and machine learning (AG Sattler). We develop data-driven approaches to antimicrobial resistance diagnostics and investigate the genomic epidemiology of multidrug-resistant bacteria, combining computational analysis with experimental validation. The position offers the opportunity to obtain a doctoral degree (Dr. rer. nat.) and is embedded in national and international research consortia (DZIF, ESGEM-AMR). To view the latest work, please click here.