Stage | Master Thesis : Large Language Model applications in scientist data processing

This internship focuses on extending an existing workflow—currently optimized for scientific articles—to extract relevant data from other sources such as material datasheets and technical books. The project includes evaluating various Large Language Model tools to identify the most effective solutions for handling diverse formats and content types.
You will work in a passionate team of scientists, utilizing your skills in programming and computer sciences. The aim of this internship is to provide students with a taste of research outside academia.

Candidates should be currently pursuing a degree in data science, computer science, or software engineering. Proficiency in programming languages such as Python, with experience with Large Language Model is crucial, familiarity with GIT, too. Knowledge in materials and polymer is a plus. Strong analytical and problem-solving abilities, with attention to detail, are important.