Key responsibilities:
- Define and implement the clinical data engineering roadmap in alignment with Novartis’ data and digital strategy, collaborating with SMEs and OncDS leadership.
- Integrate advanced tools and AI/ML-ready infrastructure to support predictive modeling, multimodal analytics, and real-world data applications.
- Align clinical and pre-clinical data engineering initiatives with the broader oncology strategy.
- Lead, manage, and develop a high-performing clinical data engineering team.
- Drive strategic initiatives and partnerships across a matrixed organization.
- Oversee data ingestion, transformation, and validation processes for clinical trial data, ensuring compliance with GCP/GxP, CDISC, and SOPs.
- Collaborate with CROs and internal teams to optimize data flow, versioning, and retention policies.
- Build and optimize data pipelines for structured and unstructured clinical data for advanced analytics.
- Deploy solutions for data harmonization, metadata management, and interoperability across Foundry, Domino, Snowflake, and POSIT Connect.
- Develop and manage applications and visualization tools to support clinical decision-making and AI-driven oncology initiatives.
Essential requirements:
- Onsite at Cambridge, MA; 0–3% travel.
- Master’s degree in CS/Bioinformatics/Data Engineering/Software Engineering or related (PhD preferred).
- 10+ years’ hands-on experience architecting and managing clinical data engineering/data management/bioinformatics solutions.
- Expertise scaling clinical development data infrastructure, including AI/ML-driven analytics and multimodal integration.
- Ability to operationalize end-to-end assay data generation/processing pipelines (automation, orchestration, compliance).
- Oncology clinical trials experience, including regulatory-compliant biomarker data management and CDISC (SDTM/ADaM).
- Familiarity with FAIR principles, data harmonization, and enterprise data governance.
- Strong technical leadership and stakeholder management.
Desirable requirements:
- Experience leading cross-functional oncology data science initiatives (translational science, biomarker analysis, real-world data, exploratory research); NGS and modern bioinformatics tools.
- Cloud-native/data lake/visualization proficiency (RShiny, Dash, Spotfire); programming (R, Python, Java, shell scripting, Linux, HPC) and knowledge of GxP/Agile/AI-ML operations.