Massimiliano Ruocco

PhD Candidate in Machine Learning for Temporal and Spatiotemporal Data The Department of Computer Science at the Norwegian University of Science and Technology (NTNU) in Trondheim, Norway, invites applications for a four-year PhD position in machine learning. The project is part of STRIDE, an interdisciplinary initiative studying the resilience of transport systems under disruptions. The research will develop deep-learning methods for temporal and spatiotemporal data, including multivariate time series observed on graph nodes and edges. Key themes include time-series forecasting under distribution shift, time-series foundation models, synthetic-data pretraining, spatiotemporal graph neural networks, and anomaly detection and localization of disruptions. Transport networks will provide the primary testbed. The successful candidate will join NTNU's Data and Artificial Intelligence (DART) group, collaborate with researchers across transport modelling, artificial intelligence, operations research, civil engineering, and science and technology studies, publish in leading venues, release code and benchmarks openly, and participate in conferences or research stays. The appointment includes three years of doctoral research and one year of career-promoting work, including teaching. Applicants need a relevant Master's degree with a substantial independent project, normally a B average or better, strong preparation in deep learning, probability, statistics and linear algebra, English communication skills, Python programming, and experience with PyTorch or JAX. Experience with transformers, foundation models, graph neural networks, forecasting, anomaly detection, or public research code is advantageous. The salary is normally NOK 580,000 gross annually, subject to qualifications and seniority, with access to NTNU computing resources, GPUs, career support, a mentor programme, pension benefits, and other employee benefits. The application deadline is 20 November 2026. Applications must include academic transcripts and diplomas, CV, Master's thesis or draft, research statement, motivation letter, relevant publications or code, and three referees.