Principal Data Scientist, R&D Oncology

Principal Data Scientist, R&D Oncology

Johnson & Johnson Innovative Medicine is recruiting for a Principal Data Scientist, R&D Oncology to join our Data Science and Digital Health team (DSDH). This position will be located at one of our offices in either Spring House PA (preferred), Cambridge MA, or San Diego CA (La Jolla area). Consideration may be given for our Titusville and Raritan, NJ locations.

The Principal Data Scientist, R&D Oncology will support how we advance data capture, build and optimize data workflows and store data by designing and implementing engineering requirements. This role will focus on applications in Oncology R&D and support data projects from across the business including Clinical, Pre-Clinical, RWD and 'omics platforms. This role will be a leading technical contributor and creative problem solver with developing AI-ready data and other routinely used data applications for Oncology R&D.

Key Responsibilities:

• Design, develop and maintain data pipelines for acquiring, managing and storing Oncology R&D data from diverse sources (e.g. biomarker labs, real-world data sources, pre-clinical applications)
• Work closely with Data Science and Oncology R&D partners to understand, document and prioritize business requirements. Translate these business needs in to high quality data products.
• Work closely with other technical leaders, such as Ontology and Knowledge graph Engineers to design and deliver future-proof, AI-ready data systems aligned with Oncology R&D business needs.
• Develop Oncology R&D-specific data repositories by implementing standard enterprise-level data models and create new data models as needed. Leverage cloud-based technology platform to accomplish goals, such as building and maintaining data repositories using AWS S3.
• Create and optimize data flows for structured and unstructured data using technologies such as Python, R, SQL, AWS services and other relevant tools.
• Implement quality and performance standards and measure KPIs to determine accuracy and consistency
• Leverage and implement data versioning and lineage tracking to support data traceability, compliance, maintaining documentation for data architectures and workflows.
• In adherence to internal standards, implement software development best practices such as Code Versioning, DevOps.

Required Qualifications:

• Advanced degree (Master's or equivalent) in Computer Science, Engineering, Life Sciences, or other relevant field is strongly preferred. (Bachelor's Degree with experience equivalency may be considered.)
• 3+ years of experience in data engineering, including data modeling and database design, preferably in the healthcare industry
• Proficiency in data engineering tools such as Python, R and SQL for data processing as well as cloud architecture (e.g. AWS services, Redshift, FSx, Glue, Lambda.
• Experience with unstructured database technologies (e.g. NoSQL) as well as other database types (e.g. Graph).
• Strong skills in analysis, problem-solving, organizational change, project delivery, and managing external vendors.
• Proven record leading improvement initiatives with multi-disciplinary and remote partners.
• Demonstrated stakeholder management capabilities- including requirements gathering, business analysis and planning. Must have the capacity to translate discussions into user requirements and project plans.
• Ability to manage a numerous projects simultaneously, prioritize work, exhibit organizational skills and flexibility to deliver maximum business value.
• Willingness to conduct periodic travel (<15% of time) to conferences and internal meetings.

Preferred Qualifications:

• Experience with healthcare data standards (e.g. CDISC, HL7, FHIR, SNOMED CT, OMOP, DICOM).
• Exposure to high dimensional data technologies and handling, including imaging.
• Familiarity with machine learning operations (MLOps) and model deployment.