Research Internship at CKI - Foundation Models for Quantum Material Design

Position: Research Internship at CKI

Project: Foundation Models for Quantum Material Design

Scientific supervisor: Prof. Dr. Andrey Ustyuzhanin

Introduction to CKI:

The Constructor Knowledge Institute (CKI) intends to set the worldwide standard for research into Computer Science, AI and Machine Learning, Robotics, and Neuroscience, operating in strong contact with industry, and:

• Leveraging CS technologies to address challenges in various fields, delivering innovative solutions tailored to industry needs.
• Providing research opportunities, mentorship, and involvement in collaborative projects to young researchers and PhDs.
• Encouraging interdisciplinary research by fostering collaboration between diverse fields, emphasizing the integration of theoretical research with practical application

Project: Foundation Models for Quantum Material Design

This project aims to develop foundation models (large, pre-trained AI models) tailored for the design of quantum materials. These models will be trained to understand the complex, high-dimensional relationships between material properties, quantum mechanical behaviors, and experimental data, allowing for the efficient design of novel materials with specific quantum characteristics. The project will explore how to apply AI models, particularly large-scale neural networks, to predict material properties such as electronic structure, magnetism, superconductivity, and more, based on quantum mechanical principles. It will also focus on integrating data from experiments and simulations to optimize the design process, reducing the need for exhaustive trial-and-error experimentation.

Challenges / key research questions:

• Capture the intricate, non-linear relationships governing quantum materials.
• Integrate quantum mechanical principles with materials science and experimental data.
• Ensure the foundation models generalize across various material systems.
• Balance model complexity with computational efficiency for large-scale predictions.
• Achieve high accuracy in predicting properties that are yet to be experimentally observed

Requirements:

• Python skills
• Experience with AI libraries
• Prompt engineering
• Math and data processing skills are plus