Senior Data Scientist – Ontology

This is a fully remote position, open to applicants in United States.

📋 Description

• Design and oversee the ontology across canonical structural, source data, and process layers.

• Establish criteria for identifying when records from various systems pertain to the same entity, based on specific use cases.

• Develop mappings from trading partner source data to the canonical ontology, ensuring documented provenance and validity conditions.

• Write OWL 2 axioms and verify logical consistency utilizing reasoners.

• Manage the ontology lifecycle using tools such as ROBOT and SHACL.

• Collaborate with the governance team and adhere to best practices.

• Discover ontologies from data rather than relying solely on schema declarations and metadata.

• Construct, direct, and assess LLM-assisted ontology extraction pipelines.

• Define and uphold human-in-the-loop validation standards for AI-generated ontological candidates.

• Work together with data quality engineers to create formal feedback mechanisms.

• Translate formal ontology decisions into specifications and implementations for graph and relational databases.

• Specify and implement SPARQL queries and graph schema requirements.

• Partner with domain experts, data engineers, product managers, integration partners, and other stakeholders.

• Keep abreast of advancements in formal ontology, knowledge representation, and LLM-assisted knowledge engineering.

⛳️ Requirements

• More than 4 years of experience in knowledge engineering, ontology development, or a closely related field in formal methods.

• Fluency in OWL 2 and description logics.

• Practical knowledge of at least one upper ontology, such as BFO.

• Proficient in RDF, OWL, and SPARQL; familiarity with LPG and Cypher.

• Understanding of schema matching, mapping semantics, entity resolution, and multi-source alignment.

• Ability to interpret functional dependencies and inclusion dependencies as signals for ontology.

• Familiarity with LLM-assisted ontology extraction and enrichment pipelines.

• Proven experience in building and maintaining domain ontologies using Protege or similar tools, with reasoner-validated consistency.

• Experience with ROBOT or ODK, or similar ontology lifecycle management tools.

• Expertise in SPARQL and/or Cypher.

• Experience in translating data profiling outputs into formal ontological assertions.

• Experience with empirical ontology discovery and top-down ontology design.

• Experience in directing or assessing LLM-assisted knowledge extraction pipelines with formal validation criteria.

• Proficiency in Python or a similar programming language.

• Experience working in multidisciplinary teams.

• A bachelor's or advanced degree in a relevant field is preferred, but not mandatory.

• Familiarity with category theory, CQL/AQL, or categorical database theory is preferred or considered a plus.

• Experience with LinkML is preferred.

• Knowledge of the healthcare supply chain domain is preferred.

• Experience with BFO 2.0 and OBO Foundry principles is preferred.

• Familiarity with provenance models is preferred.

• Experience with production-scale graph database platforms is preferred.

🏝️ Benefits

• Equal employment opportunities and consideration without regard to protected status.

• Working environment designed to empower employees to be productive and perform at their best.

• Comprehensive benefits are referenced in the EEO policy, although no specific benefits are detailed.