Candidate must have a strong interest and background in the creation of computational data from High Fidelity Computational Continuum Mechanics (CCM) Simulations i.e. CFD CSD 6-DOF Dynamics using open source solvers for multi-phase fluid dynamics of the air-sea interface to provide estimates of unsteady aerodynamic and wave loading on offshore superstructures creation of reduced order models from these high fidelity data to train physics informed deep learning networks for fast and reliable hydrodynamic and wave load predictions on marine offshore superstructures.
While the candidate is expected to have experience working with open source CCM tools such as OpenFOAM Fluidity SPH and FENICS and as this is a project in progress the interest in developing tools using DualSPHysics will be of prime interest for this position. The candidate must be familiar with Linux OS and parallel computing technologies and be adept at using High Performance Computing Platforms such as multi-core and GPU systems for all high fidelity computational simulations.
Candidate should be interested in model order reduction techniques and able to use these data to construct reliable machine learning surrogates for prediction using Tensorflow / deep learning / python tools and be able to demonstrate this capability and is expected to build on the existing efforts in progress in this area for which training data is generated using DualSPHysics.
