Agentic AI Data Engineer - CMC Data Integration

Role: AI Data Engineer specializing in pharmaceutical data infrastructure within Lilly's Bioproduct Research and Development. Objectives: develop and maintain data ingestion pipelines and a unified CMC data model to support modernized data backbone for biopharma formulations including insulins, monoclonal antibodies, and gene therapies. Responsibilities: design and implement agentic pipeline components (e.g., extraction, schema mapping, validation), build human-in-the-loop workflows for data quality and compliance, develop robust AI-assisted ingestion pipelines for unstructured data sources such as PDFs, Excel, and vendor exports; ensure pipeline health, data integrity, and GxP compliance. Qualifications: MS in Computer Science/Engineering or BS with 3–5 years' relevant experience; strong Python and SQL skills; experience with ETL pipelines from unstructured sources; familiarity with cloud platforms (Azure/AWS), data orchestration tools, and MLOps in regulated environments. Preferences: knowledge of 21 CFR Part 11, GxP data principles, LIMS/ELN systems integration, pharmaceutical CMC data types, and data mesh architectures. Collaboration involves working with scientists, digital architects, and external CDMO partners; role is hybrid in Indianapolis, with no specified travel requirements.