PhD Position: Remote Sensing, Physics-Based Modeling, and Bayesian Machine Learning for Bridge Risk Management

Join an international research collaboration between the Technical University of Munich (TUM) and Politecnico di Milano to develop innovative methods for risk management in bridge portfolios. This funded PhD position is based in the Engineering Risk Analysis Group at TUM, a team specializing in uncertainty quantification, engineering reliability, and risk & decision analysis for optimal and sustainable decision-making in engineering and environmental systems. The group operates at the intersection of engineering, data science, and applied mathematics, providing a dynamic and flexible work environment in the heart of Munich. The project addresses the challenges of aging infrastructure, focusing on the development of new methodologies that combine remote sensing, physics-based modeling, and Bayesian machine learning. The goal is to create tools that transform complex data into actionable insights for infrastructure safety and sustainability. You will develop risk assessment methodologies for bridges and civil infrastructure, integrating remote sensing data with physics-based models into a probabilistic decision support system. A key aspect of the research is establishing a systematic uncertainty quantification framework for remote sensing data, which will underpin Bayesian machine learning approaches to predict bridge deformations and manage uncertainty. The project will also leverage additional data sources within bridge portfolios to further reduce prediction uncertainty, ultimately resulting in methods and tools for effective bridge portfolio management. This position offers an excellent international research environment, including the opportunity for an extended research visit at Politecnico di Milano in Italy. The earliest starting date is February 1, 2026, and the successful candidate will be enrolled in the doctoral program at TUM. The position is funded at 75% TV-L E13, with financial support from the TUM Institute of Advanced Studies and the TUM Georg Nemetschek Institute of Artificial Intelligence for the Built World. Applicants should hold an M.Sc. degree in a relevant field, demonstrate excellent academic performance, and have experience with stochastic methods, risk and reliability analysis, and data analysis. Programming skills in Python, MATLAB, C/C++, or similar languages are required, along with strong analytical and quantitative abilities. Proficiency in English is essential, and knowledge of German is advantageous. The team values strong communication skills and a collaborative spirit. To apply, send a single PDF containing your CV, electronic copies of academic diplomas, and a short cover letter (maximum one page) outlining your interest in the position and relevant experience to [email protected]. Applications are reviewed on a rolling basis, and preference is given to disabled applicants if equally qualified. For more information, refer to the official position description and application portal linked below. Full Position Description (PDF) Application Portal