R&D Data Scientist
Job Description
Elanco is hiring an R&D Data Scientist to define and operationalize R&D-wide data governance and systems that keep scientific data lineage-tracked and AI-ready.
Responsibilities
- Support interoperability of R&D data across R&D and enterprise-wide ecosystems.
- Advise on critical R&D data attributes, controlled vocabularies, schemas, and master data entities needed for cross-system interoperability.
- Optimize data capture, extraction, and standardization across preclinical and clinical workflows to enable machine learning, generative AI, and predictive modeling.
- Establish automated data quality frameworks, lineage monitoring, and compliance controls using FAIR principles, GxP, and ALCOA+ across interconnected scientific systems.
- Author and govern enterprise-wide data policies, standards, data classification, and operating procedures across R&D software platforms, aligning scientific workflows with enterprise IT architecture.
- Evaluate data models across scientific applications to determine what must be controlled at the enterprise level (for example: compound IDs, study attributes, subject identifiers, assay parameters) versus local configuration.
- Define standardized ontologies and controlled vocabularies to support consistent data representation.
- Serve as lead data science advisor for core discovery and development platforms, including:
- ARCHI: standardize enterprise architecture definitions, repository schemas, and data pipelines.
- Benchling: oversee schema design, entity registration, inventory tracking, and API-based data extraction for downstream analytics.
- Revvity: guide assay data capture, screening data harmonization, and analytical workflow standardization.
- Clinical Systems: ensure clinical trial data attributes (EDC, CTMS, CDISC/SDTM models) meet enterprise standards for traceability and submission readiness.
- Design, build, and deploy machine learning and statistical models using harmonized data assets from Benchling, Revvity, and clinical platforms (for example: predictive screening and clinical outcome modeling).
- Implement automated data validation, anomaly detection, and data completeness metrics at enterprise ingestion points.
- Partner with stakeholders across Discovery, Translational Medicine, Clinical Operations, Regulatory, Quality Assurance, and IT to drive governance adoption without reducing scientific velocity.
- Collaborate with Data Engineers, ML Engineers, and Cloud Solution Architects (Azure / GCP) to design scalable data pipelines, data mesh/lakehouse architectures, and secure data access layers.
- Embed FAIR data principles and ensure data governance workflows meet regulatory standards including GxP, 21 CFR Part 11, and ALCOA+ data integrity guidelines.
Requirements
- BS or MS in Data Science (or related quantitative/life sciences discipline).
- 8+ years of relevant experience in Data Science, R&D Informatics, or Data Architecture within Life Sciences, Biotechnology, Animal Health, or Pharmaceuticals.
- Proven experience designing data governance policies, attribute-level master data management (MDM), data catalogs, data dictionaries, and enterprise data models from a systems perspective.
- Hands-on experience integrating life science platforms, including:
- Electronic Lab Notebooks & Registries (for example: Benchling).
- Scientific Informatics & Chemistry/Biology platforms (for example: Revvity Signals, PerkinElmer informatics).
- Architecture & enterprise modeling tools (for example: ARCHI / ArchiMate).
- Clinical data platforms (EDC, CTMS, CDISC standards).
- Strong programming skills in Python or R, plus advanced SQL for relational, document, and graph database querying.
- Demonstrated experience applying statistical and machine learning models (for example: classification, regression, clustering, NLP for scientific text, predictive modeling).
- Ability to translate complex data architecture and analytics concepts into actionable guidance for scientific, operational, and executive stakeholders.
Technologies
- Python, R, SQL
- Azure, GCP
- ARCHI, ArchiMate
- Benchling, Revvity
- ELN, EDC, CTMS, CDISC, SDTM, ADaM
- MeSH, SNOMED, ChEMBL
- ALCOA+, GxP, 21 CFR Part 11
- REST APIs, ETL/ELT
- Snowflake, Databricks, Azure Synapse, Purview, Data Factory
- NLP, data mesh, lakehouse
Benefits
- Multiple relocation packages
- Two weeklong shutdowns (mid-summer and year-end) in the US (in addition to PTO)
- 8-week parental leave
- 9 Employee Resource Groups
- Annual bonus offering
- Flexible work arrangements
- Up to 6% 401K matching
Preferred Qualifications
- Deep familiarity with biomedical ontologies (for example: MeSH, SNOMED, ChEMBL, CDISC/SDTM/ADaM) and FAIR data implementation frameworks.
- Experience with REST APIs, ETL/ELT pipelines, and integrating scientific SaaS platforms into enterprise data lakes/lakehouses (for example: Snowflake, Databricks).
- Familiarity with data and analytics services across Microsoft Azure (for example: Azure Synapse, Purview, Data Factory) and/or Google Cloud Platform (GCP).
- Working knowledge of GxP, 21 CFR Part 11, data privacy requirements, and computerized system validation (CSV) in life science environments.