Algorithm Developer III - AI/ML for Semiconductors

Applied Materials, Inc.; Santa Clara (CA); On-site; USD 161,000 - 221,000; Full time

Job summary

Applied Materials, Inc. is seeking an Algorithm Developer to work at the intersection of AI/ML, physics, and systems engineering for next-generation semiconductor manufacturing applications.

The role focuses on ingesting sensor data, extracting physics-based relationships, and building predictive and control models with a hybrid physics-first and machine learning approach to optimize real-time processes.

Qualifications

• PhD in Physics, Applied Mathematics, Computational Chemistry, Electrical/Mechanical Engineering or related field, or Master’s with relevant experience.
• Proven ability to develop high-quality, maintainable code and production-ready software.
• Experience with computational methods, CAE, physical modeling, or simulation of complex systems, and ML applications.

Responsibilities

• Design scalable data pipelines to collect, process, and analyze high-volume sensor data from semiconductor manufacturing systems.
• Identify and model physical relationships governing complex process behavior.
• Develop predictive and control algorithms combining physics-based methods with ML approaches.
• Build robust software modules that integrate with real-world manufacturing tools.
• Collaborate with physics, engineering, software, and data science teams to accelerate innovation.
• Develop ML surrogates or reduced-order models based on physics simulations.

Skills

Theoretical physics

Applied mathematics

Machine learning

Software development

Education

Ph.D. in Physics

Master’s degree in a quantitative field with 2+ years experience

Job description

Applied Materials, Inc. is seeking an Algorithm Developer to work at the intersection of AI/ML, physics, and systems engineering for next-generation semiconductor manufacturing applications.

The role focuses on ingesting sensor data, extracting physics-based relationships, and building predictive and control models with a hybrid physics-first and machine learning approach to optimize real-time processes.