Data Scientist for Research Project (Fixed-Term) | Data Scientist / Datenwissenschaftler (m/w/d) im Rahmen eines Forschungsprojekts befristet

Job Summary

This role involves working as a Data Scientist on a fixed-term research project focused on AI-generated cancer registry reports, contributing significantly to the fight against cancer in North Rhine-Westphalia (NRW). The successful candidate will be responsible for implementing and advancing a Large Language Model (LLM) pipeline using open-source AI frameworks on proprietary hardware for information extraction from diverse sources. Key tasks include setting up and operating an AI server for training and inference, co-developing an evaluation concept to measure the data quality of AI-generated reports, and conducting thorough evaluations and analysis. Candidates must possess a Master's degree in Data Science, Computer Science, or a related field, coupled with strong expertise in statistics, Machine Learning, and Deep Learning, particularly focusing on LLMs. Experience with Python, common ML/LLM frameworks (like PyTorch or LangChain), and operating AI systems on private hardware (Linux, Docker) is essential. This is an attractive opportunity to apply cutting-edge AI techniques to critical public health research.