AI Enabled Device Modeling
Core
Develop AI-enabled methods for semiconductor device modeling to accelerate model extraction, improve predictive accuracy, and create scalable workflows for CMOS, cryogenic, photonic, and superconducting devices.
Role type
New graduate machine learning engineer (semiconductor device modeling)
Builds
AI-enabled device modeling workflows and design-enablement solutions
Domain
Semiconductor manufacturing / Physics-informed machine learning
Deliverable
production ML models
Required skills
Python, machine learning, deep learning, semiconductor device physics, data pipelines, model validation, optimization, feature engineering
Preferred skills
physics-informed neural networks, Bayesian optimization, Gaussian processes, experiment tracking, high-performance computing, Linux
Technologies
PyTorch, TensorFlow, JAX, NumPy, pandas, SciPy, scikit-learn, Git, MLflow, Weights & Biases
Responsibilities
Develop and evaluate ML methods for parameter extraction and surrogate modeling; Build reproducible data pipelines combining measured data and simulations; Train and validate AI/ML models with physics-based constraints; Automate model fitting and reporting; Collaborate with device and design teams to translate requirements into solutions.
Seniority
Junior, new graduate
