1) Develop and implement Machine Learning and Deep Learning models for engineering and automotive applications.
2) Identify engineering problems that can be addressed using AI/ML, predictive analytics, and data-driven approaches.
3) Build predictive and surrogate models to estimate simulation/engineering outputs and reduce computational effort.
4) Develop Physics-Informed Machine Learning (PINNs) and physics-guided ML models for engineering applications.
5) Develop models using Python, PyTorch/TensorFlow, Scikit-learn, NumPy, Pandas, and other relevant ML frameworks.
6) Explore and implement Deep Learning, CNNs, RNNs/LSTMs, Transformers, GNNs, and other suitable architectures based on the problem.
7) Build AI-driven optimization and Design of Experiments (DoE) approaches for engineering design problems.
8) Experience with PhysicsNeMo (formerly NVIDIA Modulus) or similar physics-informed / physics-ML frameworks for developing AI/ML models for engineering and simulation applications.
9) Experience in CAE/automotive simulation is an added advantage, particularly exposure to tools such as LS-DYNA, ANSA, GNS Animator, or similar platforms