Senior Physics AI Scientist: Scientific ML for Semiconductors

Applied Materials; Santa Clara (CA); On-site; USD 143,000 - 197,000; Full time

Job summary

Applied Materials is seeking a Senior AI/ML Engineer to develop next-generation AI models for semiconductor engineering, combining domain knowledge with advanced machine learning techniques.

You will build physics-aware surrogate and foundation models, design optimization workflows, and collaborate with engineers to solve complex challenges, accelerating simulations and design processes.

Qualifications

• Ph.D. in Mechanical Engineering, Chemical Engineering, Materials Science, Physics, Applied Mathematics, or Computer Science.
• Experience applying machine learning to real-world scientific or engineering problems.
• Strong background in scientific machine learning and numerical simulation.
• Experience with surrogate modeling, PINNs, operator learning (e.g., FNO), or foundation models.
• Proficiency in Python and PyTorch.
• Experience with HPC, distributed training, large-scale scientific datasets or scalable ML workflows.

Responsibilities

• Develop next-generation AI models for semiconductor engineering by combining scientific domain knowledge with modern machine learning.
• Build physics-aware surrogate models, foundation models, and optimization workflows that accelerate simulation and engineering design.
• Collaborate with domain experts to formulate AI solutions for complex engineering challenges.
• Develop scalable data generation, training, validation and deployment workflows for Scientific AI models.
• Publish technical innovations and drive adoption of Scientific AI across engineering applications.

Skills

Scientific ML

Python

PyTorch

HPC

Large-scale ML workflows

Numerical simulation

Education

Ph.D. in Mechanical Engineering, Chemical Engineering, Materials Science, Physics, Applied Mathematics, or Computer Science

Tools

PyTorch

HPC frameworks

Job description

Applied Materials is seeking a Senior AI/ML Engineer to develop next-generation AI models for semiconductor engineering, combining domain knowledge with advanced machine learning techniques.

You will build physics-aware surrogate and foundation models, design optimization workflows, and collaborate with engineers to solve complex challenges, accelerating simulations and design processes.