PhD Fellowship in Surrogate Modelling of Fluid Flows using Deep Learning

The University of Stavanger is offering a PhD Fellowship in Surrogate Modelling of Fluid Flows using Deep Learning, based in the Department of Mechanical and Structural Engineering and Materials Science. This position is part of the Faculty of Science and Technology and is vacant from August 2026. The successful candidate will join a dynamic research group with established industrial collaborations and access to high-performance computing resources. The research focus is on developing deep learning techniques to accelerate the prediction of fluid flows in engineering contexts. Traditional simulation models for fluid flows are often slow, making them impractical for iterative design or optimization in industry. Recent advances in the group have demonstrated that deep learning can reduce simulation times to seconds, enabling real-time applications and significantly enhancing the usability of simulation tools for engineers. The candidate will have the opportunity to develop an independent research profile within this framework, with possible directions including improvement of deep-learning surrogate models, integration into optimization workflows, uncertainty quantification, reliability assessment, explainability and physical consistency in scientific machine learning, and expansion of application areas through dataset generation and model testing. Applicants should have a strong academic background, holding a five-year master degree or equivalent in mechanical engineering, aerospace engineering, computer science, data science, applied mathematics, or computational physics. Both the master’s thesis grade and the weighted average grade must be equivalent to or better than a B grade. Candidates with different grading systems must provide a conversion scale and Diploma Supplement. Required skills include solid knowledge of computational fluid dynamics, strong programming abilities in scientific computing (Python and/or C++), experience with machine learning workflows (preferably PyTorch and JAX), familiarity with scientific machine learning for physics-based modeling (e.g., PhysicsNeMo), and experience with simulation of complex geometries, turbulence modeling, high-performance computing or GPU acceleration, uncertainty quantification, optimization, reduced-order modeling, and open-source CFD tools such as OpenFOAM. Motivation, research potential, and the ability to work independently and in teams are emphasized. Good command of English is mandatory, with minimum scores for TOEFL (90), IELTS (6.5), CAE/CPE, or PTE Academic (62), unless exempt by prior study or degree in English. The position offers a competitive salary (NOK 550,800 gross per year), automatic membership in the Norwegian Public Service Pension Fund, favorable insurance and retirement benefits, relocation support, discounted public transport, gym and sports club membership, and guaranteed nursery places. The university provides free Norwegian language courses and access to digital mental health services. Diversity is valued, and applicants from all backgrounds are encouraged to apply. The university aims to recruit more women in the subject area and offers an inclusive workplace. To apply, candidates should submit their application via the Jobbnorge portal, including an application letter stating research interests and motivation, CV, references, certificates/diplomas, Diploma Supplement or conversion scale if required, documentation of English competence, and relevant publications. All documentation must be in English or a Scandinavian language and compressed if over 100 MB. Applications are evaluated based on information available at the deadline, and relevant candidates will be invited to interview. The appointee must reside in Stavanger and be present during ordinary working hours. The University of Stavanger is a member of the European Consortium of Innovative Universities and is located in a vibrant region with a dynamic labor market and rich cultural activities. The Faculty of Science and Technology has strong ties to research institutions and industry, with nearly 40% of its budget externally funded. The Department of Mechanical and Structural Engineering and Materials Science offers education and research in offshore technology, marine and subsea technology, offshore wind, industrial technology, civil and structural engineering, mechanical engineering, and materials engineering, with a strong international profile. For questions about the position, contact Professor Knut Erik T. Giljarhus ([email protected]) or HR advisor Rosa Cam Andrade ([email protected]).