Data Engineer, PDS&T CMC
Summary
Designs and builds data pipelines, feature stores, and governed datasets to power AI/ML models and manufacturing systems at a biopharma company.
- Architect feature stores and curated datasets
- Build CI/CD pipelines and automated testing
- Build batch and real time streaming pipelines
- Build governed versioned data products for AI ML
- Create data catalogs and access control
- Design data ingestion pipelines
- Develop harmonized data models and ontologies
- Ensure data governance for regulated compliance
- Establish pipeline observability monitoring and alerting
- Implement data quality controls and anomaly detection
- Implement infrastructure-as-code
- Integrate manufacturing and CMC source systems
- Maintain data lineage and metadata infrastructure
- Perform semantic mapping to enterprise standards
- Provide production support for pipeline uptime and freshness
- Translate model data requirements into data infrastructure