About the job
Embark on an innovative journey with ASM, where groundbreaking technology intertwines with a collaborative spirit.
For more than 55 years, ASM has led the charge in technological advancements, playing a pivotal role in shaping the future of fields such as 5G, cloud computing, AI, and autonomous vehicles. Our diverse team of over 4,500 professionals from 70 nationalities not only drives innovation but also champions diversity, inclusion, and sustainability, making a positive global impact. Our tailored development programs are designed to nurture your growth, empowering you to push the boundaries of innovation.
Internship Overview: Computational Materials Science Intern (Leuven, Belgium)
About the Internship
We invite students with a passion for computational materials science, data analytics, and AI-driven research to apply for this internship. The focus of this role is to develop structure–property relationships that accelerate the discovery of new materials, as well as preparing datasets and workflows for future AI initiatives in advanced semiconductor research.
Learning Objectives:
- Master the art of building and managing a machine-readable materials library.
- Gain insights into key descriptors and their impacts on electronic and physical properties.
- Acquire hands-on experience in computational materials science processes and data-driven modeling.
- Utilize Python-based tools for data analysis and modeling (e.g., Jupyter notebooks).
- Investigate the fusion of computational chemistry tools with data-driven property predictions.
Primary Responsibilities:
- Construct or source bulk structures for ALD-related systems using online databases and internal specifications.
- Compile and categorize literature data regarding electronic and physical properties.
- Engage in data pre-processing and feature engineering/extraction.
- Conduct descriptor calculations and evaluate their correlations with target properties.
- Perform DFT calculations to enhance database information.
- Devise and optimize predictive models for property estimation.
- Document workflows and contribute to the internal knowledge base for AI-related projects.
