Postdoctoral Fellow - Physics

The Department of Physics at the United Arab Emirates University (UAEU) invites applications for a research assistant or a postdoctoral research position in Computational Radiation Physics and AI Surrogate Modeling. The successful candidate will work on a FANR-funded research project focused on the development of physics-informed artificial intelligence (AI) surrogates for rapid radiological dose assessment and radiation transport modeling. The project aims to combine high-fidelity Monte Carlo radiation transport simulations (MCNP and GEANT4) with modern AI and Physics-Informed Neural Network (PINN) methodologies to develop fast, reliable, and uncertainty-aware surrogate models for shielding analysis, dose estimation, and regulatory decision-support applications. The position provides an excellent opportunity to work at the intersection of nuclear engineering, computational physics, radiation transport, scientific computing, and artificial intelligence. Main Responsibilities The successful candidate will be expected to: • Develop and validate MCNP and/or GEANT4 radiation transport models. • Generate benchmark datasets for shielding and dose-assessment scenarios. • Develop AI and PINN surrogate models using modern machine-learning frameworks. • Implement uncertainty quantification and validation methodologies. • Participate in model benchmarking against analytical and Monte Carlo reference solutions. • Assist in the development of prototype computational tools for regulatory applications. • Contribute to scientific publications, reports, and presentations. • Participate in mentoring graduate and undergraduate students involved in the project. Grade: 19.

• BSc/MSc (a PhD for postdoctoral) in Nuclear Engineering, Computational Physics, Radiation Physics, Medical Physics, Scientific Computing, Applied Mathematics, Computer Science, or a closely related field. • Strong background in radiation transport and/or computational physics. • Experience with Monte Carlo simulation tools such as MCNP or GEANT4. • Programming experience in Python, C/C++, MATLAB, or related scientific programming languages. • Strong analytical and problem-solving skills. • Demonstrated ability to conduct independent research and publish scientific work. Preferred qualifications: Preference will be given to candidates with experience in one or more of the following areas: • Physics-Informed Neural Networks (PINNs) • Machine learning and deep learning • PyTorch or TensorFlow • High-performance computing (HPC) • Radiation shielding and dosimetry • Uncertainty quantification

Develop and validate MCNP and/or GEANT4 radiation transport models. Generate benchmark datasets for shielding and dose-assessment scenarios. Develop AI and PINN surrogate models using modern machine-learning frameworks. Implement uncertainty quantification and validation methodologies. Participate in model benchmarking against analytical and Monte Carlo reference solutions. Assist in the development of prototype computational tools for regulatory applications. Contribute to scientific publications, reports, and presentations. Participate in mentoring graduate and undergraduate students involved in the project.