Data Scientist (Clinical Data)
Remote
Job Summary
Bridge unstructured clinical data to AI-ready assets by translating ambiguous source structures into harmonized pipelines. Design and maintain data dictionaries, schemas, and metadata models aligned with STELA's multimodal requirements. Enforce data quality control and validation frameworks to ensure integrity, completeness, and programmatic consistency of incoming partner data. Write production-grade Python code to automate data cleaning, harmonization, and ETL workflows for large-scale biobanks. Map diverse clinical data to industry-standard ontologies like SNOMED and ICD, with emphasis on oncology and immunology domains. Conduct technical alignment meetings with external partners, hospitals, and research institutions to define data delivery formats and ground-truth data structures.
Required Qualifications
- Bachelor's or Master's degree in Life Sciences, Bioinformatics, Health Informatics, Computer Science, Statistics, or a related quantitative field
- 3–5+ years of hands-on experience in clinical data management or clinical data engineering within a CRO, CMO, pharma, or biotech environment
- High proficiency in Python and standard data science libraries (e.g., Pandas, NumPy) for data manipulation, cleaning, and validation
- Strong experience with Git version control and building reusable data pipelines
- Familiarity with clinical data structures, electronic health records (EHR), case report forms (CRFs), and longitudinal clinical trial data
- Knowledge of standard clinical and biological ontologies, specifically those tailored to cancer/oncology and/or immunology datasets
- Ability to align on data delivery formats with a partner clinical teams
- Comfort working in a fast-paced start-up environment where data schemas evolve and ingest requirements must be defined from scratch
- Experience working directly with multimodal datasets (e.g., matching clinical records with omics or digital pathology imaging)
- Understanding of CDISC standards (SDTM/ADaM) combined with a modern tech-stack approach (beyond legacy SAS programming)
- Experience building or optimizing ETL pipelines for large-scale biobanks or multinational clinical consortia
Desired Qualifications
- Experience with cloud computing platforms (AWS, GCP, etc...)
- Experience building or optimizing ETL pipelines for large-scale biobanks or multinational clinical consortia
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.