Hybrid Semantic Technologies Lead na Novartis

Job Description Summary

• Lead data42’s implementation of “Semantics and Metadata standards” and be responsible of their quality across all data processing pipelines (Pre-Clinical, Clinical, Omics & RWD) from ingest to making data accessible for disease-centric multimodal analysis & investigation.
• Enable “Data Findability” through a data FAIRification process by providing the required structured data with integrating advanced ontology management and metadata standardization (e.g., MedDRA, SDTM, ADaM, WHODrug & ISO taxonomies) enabling advanced patient cohorting & analytical functionalities.
• Maintain data42 data catalog
• Design and develop metadata management systems
• Shape data42’s vision for how semantics can transform the landscape of multimodal & multidimensional data utilization in the R&D and medical continuum.

 

Job Description

Major accountabilities:

• Interface seamlessly with semantic experts across the company including the Biomedical Research (BR), Development (Clinical Operations & Analytics) and others.  Establish and implement the multimodal data roadmap for data42 contributing to identify novel drug targets and therapeutic strategies.
• Apply all FAIR principles ensuring that all data assets are properly tagged, governed and aligned with business objectives and make any data understandable for data42 end users
• Maintain data catalog of all data assets managed across the data42 ecosystem
• Brings expertise and supports the implementation of the standardization of data models and reference data across all master data defined by each data assets owner.
• Maintain AI-enabled metadata tools to facilitate data findability and metadata management across all data assets and expose them to data42 end users.
• Lead and coordinate pipelines teams towards implementing data42’s vision for enabling disease-centric multimodal investigation. 
• Coordinate closely with teams working on semantics and metadata standards across Novartis. 
• In conjunction with a scrum master, run the team through an agile methodology

Key performance indicators:

• Support the vision of releasing a disease-centric multimodal investigation across RDC continuum. 
• Business value measures (cost savings, data rationalization, storage costs, etc.).
• Demonstration of improved speed to TAs insights generation through semantics implementations.

Impact on the organization:

• Success in building a large, scalable, and integrated data platform redefining the role of data in building disease-centric assets & insights across R&D continuum.
• Enabling multimodal & multidimensional data framework to represent, organize, and analyze complex biomedical data, enhancing R&D efficiency and innovation.

Minimum Requirements:

Education:

• A Master’s degree or higher (PhD preferred) in Computer Science, Engineering, Ontology, Semantics, Artificial Intelligence (AI) with applications in the pharmaceutical or biotechnology or healthcare sectors.

Work Experience:

• Cross Cultural Experience.
• People Leadership.
• Project Management.

Skills:

• 10+ years of professional experience in metadata management, semantic technologies, ontology, Artificial Intelligence (AI), and insights generation, within the pharmaceutical, biotechnology, or a related industry.
• In-depth knowledge of industry standardization like CDISC (SDTM, ADaM, SEND), HL7 FHIR, NCI, MedDRA, and WHODrug.
• Demonstrated experience in leading and implementing large-scale data projects and initiatives, particularly those involving semantic technologies, ontologies, and knowledge graphs.
• Proficiency in FAIR (Findable, Accessible, Interoperable, and Reusable) data principles and their application in a business/biomedical context.
• Experience with regulated environments such as GDPR and/or GxP when working with products, tools, and medical & pharmaceutical data sources.
• In-depth knowledge of Ontological authoring & engineering e.g. ontology development process, ontology life cycle, methodologies, tools and languages required for building ontologies.
• Knowledge of Generative AI and Large Language Models (LLM), with a focus on leveraging these technologies to transform unstructured and unharmonized data sources into insightful and actionable information.
• Semantic Web Technologies (Web 2.0/3.0, RDF/OWL/SKOS, SPARQL...)  and their application to the biomedical domain (OBO).
• Good knowledge of Master Data Management (MDM) & Reference Data Management (RDM) and Data Catalog (DC) concepts/technologies.
• Palantir Foundry experience preferable

Languages :

• Fluent in English (oral and written)

 

Skills Desired

Clinical Data Management, Cross-Functional Team, Data Architecture, Data Governance, Data Management, Data Quality, Data Science, Data Strategy, Drug Development, Master Data, People Management, Waterfall Model Candidatar-se agora