How graph nodes point back to source systems through schema mapping.
How the KG will be used in RAG, LLM context grounding, or reasoning pipelines.
Implement ontology-driven schemas using RDF stores or labeled-property graph stores.
3. Source System Mapping
Parse schemas from policy admin, claims, CRM, billing, and underwriting systems.
Map source fields to ontology entities using
Schema parsing
Semantic mapping
Transformation rules
Ensure semantic alignment and consistency across diverse insurance systems.
4. Azure Cloud Integration
Deploy and operationalize ontology and KG components using
Azure Data Lake / Storage
Azure Purview / Microsoft Fabric Catalog
Azure Cognitive Search (for semantic indexing)
Azure Kubernetes Services / Azure Functions (for KG pipelines)
Azure OpenAI (for semantic enrichment, RAG, and reasoning)
Integrate KG metadata into Azure metadata and lineage systems.
5. Collaboration & Governance
Work closely with
Underwriting SMEs
Claims SMEs
Data governance teams
Data engineering teams
AI/ML product teams
Document semantic models, maintain change logs, and drive ontology versioning.
Required Skills (Non-Negotiable)
Hands-on experience in ontology development, not just graph querying.
Strong knowledge of
OWL, RDF, RDFS, SKOS
SPARQL, SHACL (preferred)
Experience designing conceptual and logical domain models.
Demonstrated ability to build a knowledge graph from scratch, not just use one.
Strong insurance domain understanding
Policy structures
Exposure / risk modeling fundamentals
Claims life cycle
Product hierarchies
Regulatory constraints
Ability to map enterprise source schemas to semantic models.
Experience with at least one semantic technology stack
Stardog, GraphDB, Neo4j (with RDF frameworks), TopQuadrant, AllegroGraph, etc.
Nice-to-Have Skills
Experience building LLM-integrated semantic pipelines
Context engineering
RAG indexing
Metadata grounding
Familiarity with Azure OpenAI or similar LLM orchestration frameworks.
Understanding of industry data standards such as ACORD.
Soft Skills
Strong analytical and conceptual modeling skills.
Ability to challenge assumptions and define canonical definitions.
Ability to communicate with business SMEs and translate domain knowledge into ontology structures.
Structured documentation and versioning discipline.
Why This Role Matters
This role is foundational to
Enterprise LLM adoption
Semantic search
Knowledge-driven underwriting & claims workflows
Data governance
AI safety & consistency
Eliminating redundant and fragmented data definitions across systems
If you like wild growth and working with happy, enthusiastic over-achievers, you'll enjoy your career with us!
Not the right fit? Let us know you're interested in a future opportunity by clicking Introduce Yourself in the top-right corner of the page or create an account to set up email alerts as new job postings become available that meet your interest!
