Advisor, Knowledge Engineering and Data Management

About the role

The Advisor, Knowledge Engineering and Data Management will lead the development and governance of semantic and data management capabilities for DDCS. This role will create, maintain, and govern ontologies, taxonomies, controlled vocabularies, metadata, and knowledge graph assets that transform fragmented technical information into connected, reusable, and trusted knowledge. This position is focused on the semantic and governance foundation required for search, traceability, analytics, knowledge discovery, and AI-enabled applications. Part of the role will involve hands-on agentic AI development, building agents and large language model applications that are grounded in DDCS knowledge assets. This work is anchored in a strong semantic and data management foundation, so that the AI systems the role helps build remain trustworthy, well-governed, and traceable to authoritative sources.

Responsibilities

• Design and maintain ontologies, taxonomies, controlled vocabularies, and semantic models for DDCS concepts such as device components, materials, formulations, test methods, requirements, design outputs, quality events, manufacturing processes, and connected-device data.
• Partner with device engineers, formulation scientists, quality professionals, regulatory experts, manufacturing stakeholders, and digital teams to translate domain knowledge into practical semantic models and reusable data assets.
• Establish ownership, stewardship, metadata, lineage, change control, versioning, release management, and lifecycle practices for shared semantic and knowledge graph assets.
• Work with source-system owners to improve data definitions, source authority, semantic consistency, traceability, and quality across structured and unstructured information.
• Design, build, and operate knowledge graph capabilities that integrate information from engineering systems, quality systems, PLM platforms, laboratory systems, manufacturing systems, document repositories, and other enterprise sources.
• Develop approaches for entity resolution, metadata harmonization, semantic enrichment, and relationship modeling across DDCS information assets.
• Enable semantic search, graph-backed retrieval, entity extraction, and AI-ready knowledge structures grounded in governed DDCS data assets.
• Design, build, and evaluate AI agents and large language model applications, including retrieval augmented generation and graph based retrieval, that are grounded in governed DDCS knowledge assets and validated for regulated use.
• Apply version control, automated testing, validation, monitoring, and documentation practices appropriate for regulated environments and intended use.
• Communicate modeling decisions, governance expectations, assumptions, and limitations clearly to technical and non-technical stakeholders.
• Mentor and guide scientists, engineers, analysts, and data professionals on practical use of semantic technologies and data management practices.

Basic Requirements

• Master's degree in Information Science, Data Science, Computer Science, Engineering, Biomedical Informatics, Bioinformatics, or a related quantitative discipline, with a minimum of 5 years of relevant experience
• Experience developing ontologies, taxonomies, controlled vocabularies, semantic models, or knowledge graphs
• Experience with semantic technologies such as RDF, OWL, SPARQL, SHACL, or equivalent frameworks
• Python programming experience for data integration, automation, or analytics
• Experience translating scientific, engineering, business, or data requirements into technical solutions
• Demonstrated ability to collaborate with scientific, engineering, quality, regulatory, digital, and business stakeholders

Additional Preferences

• PhD with a minimum of 2 years of relevant experience
• Experience implementing knowledge graphs, semantic platforms, metadata products, or governed data assets in production environments
• Experience with data management practices such as stewardship, metadata management, lineage, data quality, data classification, or enterprise data governance
• Experience with graph databases or semantic platforms such as Neo4j, Neptune, Stardog, GraphDB, or similar technologies
• Experience in regulated industries such as pharmaceuticals, medical devices, healthcare, biotechnology, or manufacturing
• Knowledge of pharmaceutical, medical device, or combination-product development processes, including design controls, DHF, DMR, requirements traceability, complaint handling, or UDI frameworks
• Familiarity with GxP data integrity principles, ALCOA+, and life-science standards or vocabularies such as CDISC, IDMP, UNII, UCUM, or UDI/GUDID
• Experience with enterprise metadata management, data catalog, governance, LIMS, ELN, PLM, quality management, or technical document management platforms
• Experience supporting semantic search, retrieval, knowledge discovery, analytics, or AI-enabled applications using governed knowledge assets
• Experience building AI agents or agentic workflows using frameworks such as LangGraph, LangChain, LlamaIndex, AutoGen, CrewAI, or Semantic Kernel
• Experience with retrieval augmented generation (RAG) and graph based retrieval (GraphRAG) that grounds large language models in knowledge graphs and governed data, including the use of embeddings, vector search, and semantic indexing
• Familiarity with large language model orchestration, tool and function calling, and protocols for connecting agents to enterprise tools and data, such as the Model Context Protocol (MCP)
• Experience with prompt and context engineering, and with evaluating agent behavior through testing, tracing, observability, and guardrails using tools such as LangSmith or comparable evaluation frameworks
• Understanding of responsible and trustworthy AI practices, including grounding, traceability, human oversight, and validation of AI and agentic systems for regulated (GxP) environments
• Publications, patents, open-source contributions, or recognized technical leadership in semantic technologies, knowledge engineering, or data management