BRUSSELS, Belgium
Internship Explorer
Internship Explorer
Computational Fluid Dynamics (CFD) is critical in engineering but expensive at industrial scales, especially for automotive applications. Emerging machine learning surrogates promise faster predictions; their strengths differ depending on data availability, physics constraints, and geometry complexity. This AI/ML internship will benchmark data-only and physics-informed approaches for steady RANS external aerodynamics and evaluate whether adding global geometric context to an existing surface prediction workflow improves results. The goal of this work is to assess whether next‑generation ML surrogates can significantly accelerate external aerodynamics workflows, enabling faster design exploration in the automotive sector.
