Data-driven quantification of crystal quality in advanced semiconductor devices by electron microscopy

What will you do?

During this internship, you’ll focus on building a data analysis toolbox that combines traditional image processing techniques with cutting-edge machine learning approaches. Your goal? To assess the crystal quality of semiconductor devices.

TEM imaging is essential for developing these materials, but interpreting the images is the real challenge. How can we automatically detect and quantify grain boundaries, interfaces, and defects? How do we measure interface roughness at the atomic level?

To tackle these questions, you’ll explore data-driven methods that are transforming the way we analyse materials.

Your research will concentrate on:

• Exploring quantitative image processing techniques for defects in 2D materials and multi-stack interfaces.
• Validating and improving existing algorithms for TEM image analysis.
• Testing new approaches, including unsupervised algorithms.
• Explore the use of automation.
• Extend the toolbox to characterize sample/stack/structure for different materials.
• Sharing your findings through reports and publication in leading scientific journals and conferences.

Who you are?

• You hold at least a Bachelor’s degree or are currently pursuing a Master’s degree in Engineering/Science, preferably in one of the following fields: Computer Science/Engineering, Physics, Artificial Intelligence and Machine Learning (or any interdisciplinary course).
• You can work independently, meet deadlines, and take ownership of your research.
• You have a strong research interest in investigating different advanced machine learning architectures and algorithms appropriate in the context of specified problem domain as well as eagerness to advance the state-of-the-art.
• Strong Programming skills (Python, matlab skill etc.).
• You are analytical, creative, and enjoy working in a multidisciplinary environment.
• You are a team player and have strong communication skills.
• Your English is fluent, both written and spoken.