The Institute of Biomedical Informatics (BI-K) is currently searching for a PhD Researcher focusing on research and development of Large Language Models (LLMs) for biomedical data applications.
The successful candidate will contribute to cutting-edge projects involving LLMs, data analysis, and interdisciplinary collaboration to address key challenges in the biomedical field.

The successful candidate will be responsible for the following tasks:

• Research on Large Language Models (LLMs):Conduct in-depth research into the functioning, capabilities, and limitations of LLMs, with a focus on applications in biomedical data, including training and / or fine tuning
• Quantitative Data Analysis: Independently analyse and interpret quantitative data from related data sources, employing statistical and computational techniques
• ETL Pipeline Development for Data Quality and Findability: Develop, maintain, and optimise ETL pipelines to improve data quality, findability, and accessibility in line with biomedical data requirements
• Metadata Standards and Data Integration: Apply knowledge of biomedical metadata standards to assess data quality and ensure interoperability, with an interest in data integration and quality assessment
• Knowledge of FAIR Principles: Ensure all data rocesses adhere to FAIR (Findable, Accessible, Interoperable, and Reusable) principles, enhancing the transparency, accessibility, and usability of biomedical data
• Interdisciplinary Collaboration: Work closely with biomedical scientists to develop and refine innovative approaches that utilise LLMs to solve biomedical data challenges and facilitate knowledge extraction
• Benchmark Dataset Compilation: Compile, validate, and benchmark datasets to support the evaluation and performance comparison of LLMs within key biomedical use cases, adhering to FAIR data principles