Physicist/Scientist Machine Learning at Applied… · Santa…

Summary: Applied Materials is a global leader in materials engineering solutions used to produce advanced chips and displays. They are seeking a highly motivated MS or PhD-level scientist or engineer to develop and apply machine learning-based models using data from multi-dimensional, high-performance computing simulations, focusing on plasma and electromagnetic simulations. Responsibilities: - Develop and train machine learning and deep learning models using data from large-scale, multi-dimensional HPC simulations - Collaborate with domain experts to incorporate physical constraints, scientific insight, and prior knowledge into ML model design - Design workflows for data ingestion, curation, and analysis of high-volume simulation outputs - Evaluate model accuracy, generalization, and robustness across a wide range of operating conditions - Optimize models for performance, scalability, and deployment on GPU-accelerated platforms - Contribute to internal software tools, modeling frameworks, and best practices Required Qualifications: - MS or PhD in Engineering (e.g., Chemical, Electrical, Mechanical, Aerospace, Nuclear, Materials), Science (e.g., Physics, Chemistry), or Computer Science - Significant experience developing machine learning or deep learning models using data from multi‑dimensional numerical simulations (e.g., PDE‑based solvers, particle‑based simulations, multiphysics models) - Strong background in Python‑based scientific computing and ML workflows - Demonstrated experience with PyTorch or equivalent deep learning frameworks - Solid understanding of: Data preprocessing and feature engineering for large, high‑dimensional datasets, Model training, validation, and performance evaluation, Numerical methods and/or physics‑based modeling concepts Preferred Qualifications: - Experience with NVIDIA Physics NeMo, NVIDIA Modulus, or related physics‑informed or simulation‑driven ML libraries - Familiarity with GPU‑accelerated computing, CUDA‑aware workflows, and HPC environments - Exposure to physics‑informed machine learning (PIML), surrogate modeling, reduced‑order modeling, or operator learning - Publications or demonstrated research contributions in ML for physical systems or related fields Required Skills: Machine learning models, High-performance computing, Python scientific computing, Deep learning frameworks Important Skills: Data preprocessing, Numerical methods, Physics-based modeling Nice-to-Have Skills: Research contributions Benefits: Comprehensive benefits package, Participation in a bonus and a stock award program