Master Thesis Development of Retrieval-Augmented Generation, Pipeline Components

During this Master thesis, you will develop and train an ML model to parse industry-specific documents as an entry point for a Retrieval-Augmented Generation (RAG) pipeline. Your job includes the development of custom parsing and chunking tools for industry-specific documents, as well as their ingestion into a vector database. Last but not least, you will train and/or fine-tune a custom LLM model for use-case-specific applications within the scope of smart hydraulic services. Basic knowledge in Linux and hands-on experience with Python scripting are required. Basic knowledge in Machine Learning, Natural Language Processing (NLP), Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) concepts, information retrieval, vector databases or Optical Character Recognition (OCR) is preferred. Enthusiasm for bleeding-edge technology and a willingness to experiment with procedures and tools are needed. The team mainly works remotely, with mobile working within Germany as the standard mode. Monthly visits to the common team on-site days are required.