The Center for AI in Radiation Oncology (CAIRO) develops data-driven models to improve diagnosis, treatment planning, and outcome prediction in radiation oncology. The CAIRO Data Semantics Taskforce aims to establish a comprehensive data infrastructure that captures medical information in a structured, standardized, and machine-readable format to facilitate training of modern AI solutions. We are seeking to expand the CAIRO Semantics team with a dedicated medical data engineer to support the curation of real-world data sets by harnessing modern LLM solutions, designing and curating semantic data definitions and implementing automated data analytics. **What you can expect**
* Support the design and implementation of comprehensive data models and structured information for oncology * Define and standardize clinical, physical, biological, and technical data using Common Data Elements (CDEs) * Develop and apply automated systems for extracting, managing, and analyzing unstructured medical data using Natural Language Processing (NLP) * Harness Large Language Models (LLMs) and agentic AI frameworks for automated data extraction * Conduct retrospective analyses of clinical data to support ongoing AI and clinical projects within CAIRO, leveraging experience with large clinical databases (e.g., NIS, NSQIP, SEER) * Act as a bridge between clinical needs and technical execution, translating complex medical workflows into robust data structures * Be a part of an active research team across disciplines in a leading university hospital
**Your Profile**
* MD, M.SC, or PhD degree in Health Informatics, Computer Science, Data Science, Medicine, Computational Biology, Biomedical Engineering, or a closely related field * Demonstrated dual expertise, possessing both a strong technical background in data engineering/data science and medical/clinical know-how * Proven track record and hands-on experience in data semantics, data definition, and health data structuring * Str...