Data Ingestion & Lakehouse Development: Design, build, and maintain data ingestion and processing pipelines within Aktiia’s Databricks-hosted medallion Lakehouse, working under senior guidance while gradually taking on more ownership.
Clinical & Legacy Data Integration: Take an active role in ingesting, centralizing, and documenting clinical data currently spread across EDC platforms such as Castor and RedCap, databases, standalone archives, and other historically grown sources.
Data Exploration & Practical Data Archaeology: Work hands-on with unfamiliar and sometimes messy datasets, identify structures and inconsistencies, and turn unstructured situations into reliable, usable data assets.
Pipeline Development & Preprocessing: Build preprocessing and ETL/ELT pipelines that provide clean, structured, and model-ready datasets for Algorithm Development, Core Tech, Machine Learning, and Dat...