Bachelor Thesis: LLM-powered Data Preprocessing Automation - Machine Learning Pipelines
📅 Posted 1d ago
📄 Job Description
About the Role
- Analyze diverse data landscapes, including PDF documents, text files, and database entries, to understand their structure and potential.
- Conceive and implement a modern process based on Large Language Models (LLMs) to efficiently extract, structure, and validate relevant information.
- Focus on transforming extracted data into a high-quality format suitable for training Machine Learning models.
- Comprehensively evaluate the efficiency of the developed process and the quality of generated training data regarding completeness, correctness, and usability.
Requirements
- Education: Bachelor's degree in Computer Science, Business Informatics, Data Science, Software Engineering, or a comparable field.
- Experience & Know-how: First practical experience with programming languages (preferably Python), relevant libraries (e.g., TensorFlow, PyTorch), basic knowledge of various data formats (PDF, Text), and databases (SQL/NoSQL).
- Personality & Working Style: Reliable and independent work style, with the ability to integrate into a team and drive common goals.
- Daily Work: On-site presence in the office is required.
- Enthusiasm: Passion for Cloud architectures and ideally initial knowledge in Databricks.
- Languages: Business-fluent German and very good English.
