Research Associate (PostDoc)

The Berlin Institute for the Foundations of Learning and Data (BIFOLD) at TU Berlin (Prof. Dr. Stefan Haufe, Dr. Shinichi Nakajima) is looking for a research associate for an agility subproject in the field of Quality-Assured Machine Learning and Inverse Modeling in Biomedicine.

The UNIML Research Group (Prof. Dr. Haufe) is a joint professorship between TU Berlin and Physikalisch-Technische Bundesanstalt (PTB) Berlin. It focuses on developing algorithms for analyzing biomedical data (e.g., neuroimaging, clinical routine data) as well as aspects of quality assurance (e.g., uncertainty, explainability) for machine learning and artificial intelligence.

The Probability Modeling and Inference (PMI) Research Group (Dr. Nakajima) is a junior research group at BIFOLD, TU Berlin. It develops generative modeling methods, primarily for applications in physics, including lattice simulations and quantum computing, as well as approaches to inverse problems and explainable artificial intelligence.

Independent and responsible research in the field of machine learning and inverse modeling in biomedicine. Development and analysis of Bayesian and deep-learning-based algorithms for source reconstruction of neurophysiological time series (magnetoencephalography and electroencephalography, M/EEG), with particular consideration of calibrated uncertainty estimates. Development of new theoretical results on the representation of uncertainty in inverse problems. Application of the developed algorithms to quality-assured localization of neural sources in clinical or cognitive neuroscience.

Successfully completed scientific university degree (Master, Diplom or equivalent), as well as successfully completed doctoral degree in mathematics, physics, or computer science; several years of experience in machine learning and inverse modeling is required, preferably in Bayesian statistics, uncertainty modeling, and/or physics-informed neural networks; very good programming skills in Python/PyTorch are essential. Experience in the modeling and analysis of time series data, e.g., using differential equations, as well as with M/EEG data, is an advantage. Good German and/or English language skills required; willingness to acquire any missing language skills.

Please send your written application, including the reference number and the standard application materials, to Technische Universität Berlin - Die Präsidentin - Fakultät IV, Institut für Softwaretechnik und Theoretische Informatik, FG Unsicherheit, Inverse Modellierung und Maschinelles Lernen, Prof. Dr. Haufe, MAR 4-3, Marchstr. 23, 10587 Berlin* or by email (as a PDF file, max. 5 MB) to: contact@uniml.tu-berlin.de.

For cost reasons, application materials sent by mail will not be returned. Please submit copies only.

By submitting your application via email you consent to having your data electronically processed and saved. Please note that we do not provide a guaranty for the protection of your personal data when submitted as unprotected file. Please find our data protection notice acc. DSGVO (General Data Protection Regulation) at the TU staff department homepage: https://www.abt2-t.tu-berlin.de/menue/themen_a_z/datenschutzerklaerung/.

To ensure equal opportunities between women and men, applications by women with the required qualifications are explicitly desired. Qualified individuals with disabilities will be favored. The TU Berlin values the diversity of its members and is committed to the goals of equal opportunities. Applications from people of all nationalities and with a migration background are very welcome.