The University of Edinburgh, in collaboration with Heriot-Watt University, is seeking a highly motivated PhD student to join a cutting-edge research project at the intersection of machine learning and turbulent flow modeling. The project focuses on developing and training advanced machine learning and generative AI architectures, such as Generative Adversarial Networks (GANs), to improve turbulence modeling in computational fluid dynamics (CFD). Traditional turbulence models like RANS and LES often lack the accuracy needed for engineering design due to their inability to resolve fine-scale physics. This project aims to overcome these limitations by leveraging high-fidelity DNS data and data-driven approaches to reconstruct small-scale turbulent structures, similar to super-resolution techniques in computer vision. The successful candidate will work on designing high-accuracy turbulence closures using DNS datasets, pushing the frontier of ML-enhanced modeling for wall-bounded and shear-layer turbulence, and building a solid foundation in turbulence physics and modern data-driven methods. The research has broad applications, from aerodynamics to atmospheric flows, and is a critical step toward deploying ML-based models in real engineering scenarios. The position is jointly based at the University of Edinburgh School of Engineering and the Institute of Mechanical, Process and Energy Engineering (IMPEE) at Heriot-Watt University. The project is supervised by Antonio Attili and Ali Ozel, both active researchers in fluid mechanics and machine learning. The TARFS Lab offers a vibrant research environment with opportunities to collaborate on fundamental and applied problems in fluid mechanics and simulation paradigms. Funding is available through competitive PhD scholarships, including School of Engineering Studentships and EPSRC CDT in Machine Learning Systems studentships. Self-funded students with external scholarships are also encouraged to apply. The position is open only to UK candidates. Applicants should have a strong background in engineering, physics, applied mathematics, or a related field, and experience with machine learning, CFD, or turbulence modeling is highly desirable. To apply, send your CV, transcript, and cover letter to Antonio Attili at antonio.attili@ed.ac.uk. For more information, visit the TARFS Lab website or the CDT in Machine Learning Systems page. Applications are reviewed on a rolling basis.