Postdoktor i maskininlärning för utveckling av nya halvledarmaterial
Core
Developing a data-driven approach to optimize semiconductor material growth by combining machine learning with physics-based understanding of the growth process.
Role type
Postdoctoral researcher (Machine Learning for Materials Science)
Builds
Open-source computational frameworks for analyzing experimental data and identifying optimized growth parameters.
Domain
Semiconductor physics, nanotechnology, materials science, machine learning.
Deliverable
production ML models
Required skills
Machine learning, physics-based modeling, experimental data analysis, open-source software development, parameter identification for material growth.
Preferred skills
Expertise in wide bandgap semiconductors (AlN, UWBG), nanoelectronics, synchrotron radiation physics.
Technologies
Open-source computational frameworks, experimental data sets.
Responsibilities
Develop machine learning methods based on experimental data provided by collaborating experimentalists; identify and define relevant parameters for material growth based on underlying physics; develop an open-source computational framework to analyze experimental data, identify relationships between growth conditions and material properties, and suggest optimized growth parameters.
Seniority
Postdoctoral researcher (early-career independent researcher)