Post-Doctoral Fellow in Physics-Informed Machine Learning for Semiconductor Process Modeling George Washington University in United States

George Washington University and NIST are seeking a Post-Doctoral Fellow in Physics-Informed Machine Learning (PIML) for semiconductor process modeling in Gaithersburg, Maryland.

The project sits at the intersection of physics, chemistry, computer science, materials science, and mathematics, with a strong focus on atomic layer deposition (ALD), multiscale modeling, and high-fidelity digital twins for chip manufacturing. The role is tied to the CHIPS Act mission to accelerate semiconductor innovation.

Responsibilities include designing and training PIML models constrained by physical laws, developing multiscale simulations from the atomic level upward, implementing and evaluating algorithms, quantifying uncertainty, and building robust Python software tools. The fellow is also expected to present at international conferences and publish in high-impact journals.

Eligibility highlights: a Ph.D. in Chemistry, Physics, Math, Computer Science, or Data Science; familiarity with TensorFlow or PyTorch; experience with process modeling tools such as Cantera or CHEMKIN; strong Python programming skills; and the ability to work with heterogeneous data and uncertainty analysis.

This is a postdoctoral opening, not a scholarship. No stipend or salary amount is stated in the post. The application link is provided in the post, and no deadline is mentioned.