See our open position page to see all open positions.
AutoPiX – Imaging for Patient Benefit in Arthritis (two PhD positions)
Supervisors: Philipp Seeböck & Jana Eder
AutoPiX combines multimodal imaging and AI to improve diagnosis and disease monitoring in arthritis. The PhD projects focus on developing machine learning methods to detect subtle joint changes, model disease progression, and identify new imaging biomarkers. The project is part of an international consortium and provides access to one of the world's largest curated arthritis imaging datasets.
Speaking Again – AI-Driven Voice Restoration of Pathological Speech
Supervisor: Philipp Aichinger
This project develops AI methods to transform pathological voices into natural-sounding speech. It is based on real clinical voice data and carried out in collaboration between the Medical University of Vienna and Graz University of Technology.
Clinical Pathways and Decision Support for Acute Chest Pain
Supervisor: Dominik Roth
This project uses clinical routine data to develop diagnostic and prognostic models that support physicians in making decisions in emergency medicine.
Machine Learning and In Silico Modeling of Sex Differences in Temporomandibular Joint Function (two PhD positions)
Supervisor: Benedikt Sagl
This project combines machine learning and biomechanical simulation to study sex-specific differences in temporomandibular joint function. One position focuses on hybrid modeling and data analysis, the other on reinforcement learning for modeling motor control.
Deep Learning for Motion Tracking in MRI
Supervisor: Stanislav Motyka
This FWF-funded PhD project aims to develop a deep learning-driven method for real-time motion correction in MRI. The candidate will design and implement ultra-fast (<10ms) k-space MR navigators to estimate 6 DoF - head motion via Deep Learning. The project will combine MR physics, signal processing, and AI to enable high-quality imaging free from motion artefacts at ultra-high field MRI systems.
Deep Learning for real-time B0-Field Stabilisation at 7T MR Scanner
Supervisor: Stanislav Motyka
This project focuses on developing and deploying DL approaches for real-time B0-field stabilisation at 7T MR Scanner. The candidate will further developed our DL solution for prediction of changes of B0 field due to subject motion and deploy it directly at the scanner. The project integrates physics-based modelling and software engineering with AI to improve MR image and spectroscopic data quality at ultra-high field MRI systems.
2.) Deep Learning for real-time B0-Field Stabilisation at 7T MR Scanner
Application deadline: November 30, 2025
Application: exclusively via the online application tool
Contact: phdrecruitment@meduniwien.ac.at
More information about the projects and the application process can be found at
oc10.meduniwien.ac.at/en/open-phd-positions