Scientific Machine Learning Engineer

As a Scientific Machine Learning Engineer within the Methods Team, you will work at the intersection of computational science, engineering simulation, and artificial intelligence. You will develop advanced machine learning models—such as Physics-Informed Neural Networks (PINNs) and neural operators—to augment or replace computationally expensive simulations (e.g., fluid dynamics and structural analysis). Leveraging NVIDIA platforms (e.g., Physics NeMo) and GPU computing, you will help build scalable, real-time simulation tools that directly influence Ford’s product development. You will collaborate closely with simulation engineers and cross-functional teams to translate research innovations into production-ready solutions.

• Design, train, and validate Physics-Informed Neural Networks (PINNs) and neural operator models (e.g., Fourier Neural Operators, DeepONet)
• Develop surrogate models to accelerate or replace traditional simulation methods
• Implement scientific machine learning workflows using NVIDIA Physics NeMo or comparable frameworks
• Apply ML methods to automotive engineering domains, including: + Computational Fluid Dynamics (CFD) + Structural mechanics and crash simulation + Multibody dynamics
• Perform uncertainty quantification (UQ) and sensitivity analysis
• Optimise models for multi-GPU environments
• Collaborate with simulation engineers and product teams to deliver production-ready tools
• Contribute to development of digital twins and real-time simulation capabilities

Education

• Master’s or PhD in Mechanical Engineering, Computer Science, Applied Mathematics, or a related field

Experience

• 5+ years in scientific machine learning, computational engineering, or related domain

Technical Skills

• Experience with PINN frameworks (e.g., DeepXDE, NVIDIA Physics NeMo, or similar)
• Strong proficiency in Python, with experience in PyTorch or TensorFlow
• Understanding of partial differential equations (PDEs) and numerical methods
• Experience working with GPU computing and distributed training
• Familiarity with scientific computing workflows

Nice to Have

• Experience with C++ and/or CUDA
• Exposure to automotive simulation tools (CFD, FEA)
• Experience applying machine learning in engineering domains
• Familiarity with Large Language Models (LLMs) applied to engineering or simulation workflows