MSAID is looking for a working student in deep-learning at our office at the university campus in Garching, near Munich or Berlin, Germany.

MSAID is an innovative bioinformatics spin-off from the Technical University of Munich. Our interdisciplinary team specializes in the development of state-of-the-art deep learning and analytics pipelines for high-throughput protein analyses and we are looking for a strong candidate to support our development team.

The precise identification and quantification of proteins is a crucial step in the understanding, diagnosis, and treatment of diseases. Mass spectrometry-based proteomics is a powerful toolbox for the simultaneous analysis of thousands of proteins and represents the go-to technology for biomarker research and drug discovery. However, current data analysis solutions often rely on simple concepts that remained unchanged for decades – a challenge we aim to resolve.

Your contribution

  • You will contribute to MSAID’s research efforts for deep learning in molecular biology
  • You will contribute to the creation of a deep learning-based protein analysis software to aid the understanding, diagnosis, and treatment of diseases
  • You will evaluate and integrate the newest machine learning research findings into MSAID’s internal machine learning pipelines

Your profile

  • Studying Computer Science, Bioinformatics or a related field
  • Demonstrated knowledge of scientific Python (numpy, pandas)
  • Comfortable with Linux and bash
  • Highly motivated, independent learner with curiosity to explore new fields
  • Basic knowledge in machine learning, pattern recognition or data science are a plus

Our offer

  • Opportunity to apply machine learning to biological and medical data making a real impact
  • Environment for continuous professional development
  • Young and highly motivated team with a flat hierarchy
  • Relaxed startup atmosphere
  • Student positions in Munich and Berlin

We look forward to receiving your comprehensive application as a single PDF file including your earliest starting date (to Dr. Martin Frejno):

MSAID, a pioneer in transforming proteomics with deep learning, announces an exclusive license agreement with Thermo Fisher Scientific, the world leader in serving science, to develop and commercialize deep learning tools for proteomics.

“Accurately measuring the proteome is a crucial step in the understanding, diagnosis, and treatment of diseases”, said Prof. Bernhard Kuster, a leading expert in proteomics and co-founder of MSAID GmbH. “Harnessing artificial intelligence will enable us to dig deeper into proteomic data and will unlock its true potential.”

Characteristics like chromatographic retention time or fragment ion intensities in tandem mass spectra are crucial for the confident identification of peptides from experimental data. Based on vast amounts of data, artificial intelligence can learn and subsequently predict these characteristics, extrapolating beyond the initial training data. Improving on the published deep learning model Prosit [1], MSAID developed INFERYS, an artificial intelligence, which will be made available to laboratories around the world through the collaboration with Thermo Fisher Scientific.

INFERYS will enable users to predict spectral libraries of entire proteomes with the click of a button. In addition, it powers INFERYS Rescoring, which automatically calibrates INFERYS to user data and then calculates intensity-based similarity scores for peptide-spectrum-matches, thereby improving the confidence in search results.

“INFERYS is fully compatible with CPUs and end-user hardware and does not require expensive GPUs to run. This marks the beginning of a new era in proteomics where artificial intelligence is at every researcher’s fingertips,” said Martin Frejno, co-founder and CEO of MSAID GmbH. “INFERYS will dramatically increase the confidence in results of proteomics experiments and help with the analysis of particularly challenging samples commonly encountered, for example, in Immunopeptidomics experiments.”

MSAID and Thermo Fischer Scientific will present the results of their collaboration at the American Society for Mass Spectrometry (ASMS) Reboot Program, from June 1-12, 2020. Also see Thermo Fisher’s press release on our collaboration.

[1] Prosit: proteome-wide prediction of peptide tandem mass spectra by deep learning; Gessulat S, Schmidt T et al., Nature Methods 2019.


MSAID GmbH [ɛm ɛs eɪd] transforms the way scientists analyze proteomics data. MSAID is a privately-held informatics spin-off from the Technical University of Munich, Germany. The company was founded by an interdisciplinary team of scientists with the vision to provide better computational solutions to the field of proteomics. All founders have an exceptionally strong track record and long-standing expertise in the acquisition, analysis, and interpretation of proteomic data. Our ambition is to replace current algorithms for proteomics with powerful, AI-based solutions, thereby paving the way for a smarter, deeper, and more reliable way of interrogating proteomic data. For more details, please visit