Internship in Visual Representation of Technical Diagrams for LLMs - remote possible

Education: Master studies in Computer Science, Data Science, or a comparable field. Experience: Proficiency in Python and ideally prior experience in building RAG systems or chatbots. Personality: A self-driven, proactive, and solution-oriented individual with an independent work ethic. Enthusiasm: A strong passion for developing optimal solutions.

Research optimal methods for processing and representing technical diagrams for integration with LLMs. Explore challenges of multi-modal LLMs in handling visual data and propose novel solutions. Design and implement a pipeline for a synthetic dataset linking technical diagrams to textual descriptions in both directions. Investigate the influence of dataset quality and structure on model training and performance. Conduct testing of the trained model on real-world technical diagrams from various domains. Develop metrics to assess the model's interpretation and output generation capabilities. Perform comparative analysis of state-of-the-art multi-modal models to identify strengths and limitations.