Technical Architect

Job Summary

We are seeking a hands-on Ontology / Knowledge Graph Engineer to design, build, and maintain enterprise knowledge models supporting network automation, semantic search, and AI/agentic use cases. The ideal candidate combines strong RDF/OWL and graph engineering skills with practical experience converting complex, real-world data into well-defined, validated semantic models.

Key Responsibilities

• Design and evolve enterprise ontologies using RDF, RDFS, OWL, Turtle (TTL), and SHACL.
• Develop class/property hierarchies, relationships, taxonomies, namespaces, constraints, and reusable ontology patterns.
• Apply both schema-first and schema-late modeling approaches, including reverse-engineering models from existing data.
• Profile and model large, complex datasets from Excel/CSV, CIQ, configuration, inventory/CMDB, JSON, and relational sources.
• Define atomic vs. derived attributes, cross-field relationships, deterministic derivation rules, and validation rules.
• Develop SPARQL 1.1 queries, competency questions, graph traversals, dependency/impact queries, and semantic validation.
• Build and maintain ontology ingestion, transformation, validation, and testing pipelines using Python.
• Work with RDF graph databases such as GraphDB/Stardog and understand Labeled Property Graph (LPG) technologies such as Neo4j.
• Support Ontology-RAG / GraphRAG / hybrid graph + vector retrieval and integration of knowledge graphs with AI agents.
• Partner with network/domain SMEs to translate implicit business and engineering knowledge into explicit, testable models.
• Maintain ontology artifacts, specifications, mappings, and validation rules in Git/CI-CD.

Required Skills & Experience

• Strong hands-on experience with RDF, RDFS, OWL, TTL, SHACL, SPARQL, and Semantic Web technologies.
• Practical knowledge of knowledge graphs, graph traversal, RDF stores, LPGs, and graph validation.
• Experience with schema-first and schema-late ontology development.
• Strong data modeling and reverse-engineering skills, including working with messy or incomplete source data.
• Experience with JSON Schema, relational data modeling, and mapping between relational/JSON and graph models.
• Strong Python skills for data processing, validation, and automation.
• Experience with graph databases such as GraphDB, Stardog, Neo4j, or similar.
• Experience with Git and CI/CD development practices.

Preferred Qualifications

• Master’s or PhD in Data Science, Computer Science, Artificial Intelligence, Knowledge Representation, Information Science, Engineering, or a related technical field preferred.
• Telecom / 5G & 4G network domain knowledge, including network functions, transport, inventory, configuration, and network relationships.
• Experience with Kubernetes and Helm configuration data.
• Experience with Ontology-RAG (O-RAG), GraphRAG, RAG, vector databases, and AI agent integration.
• Familiarity with MCP and agentic AI architectures.
• Experience with ontology design patterns such as SKOS and PROV-O.
• Familiarity with AI-assisted engineering tools such as Claude Code

Key Responsibilities

Design and evolve enterprise ontologies using RDF, RDFS, OWL, Turtle (TTL), and SHACL.

• Develop class/property hierarchies, relationships, taxonomies, namespaces, constraints, and reusable ontology patterns.
• Apply both schema-first and schema-late modeling approaches, including reverse-engineering models from existing data.
• Profile and model large, complex datasets from Excel/CSV, CIQ, configuration, inventory/CMDB, JSON, and relational sources.
• Define atomic vs. derived attributes, cross-field relationships, deterministic derivation rules, and validation rules.
• Develop SPARQL 1.1 queries, competency questions, graph traversals, dependency/impact queries, and semantic validation.
• Build and maintain ontology ingestion, transformation, validation, and testing pipelines using Python.
• Work with RDF graph databases such as GraphDB/Stardog and understand Labeled Property Graph (LPG) technologies such as Neo4j.
• Support Ontology-RAG / GraphRAG / hybrid graph + vector retrieval and integration of knowledge graphs with AI agents.
• Partner with network/domain SMEs to translate implicit business and engineering knowledge into explicit, testable models.
• Maintain ontology artifacts, specifications, mappings, and validation rules in Git/CI-CD.

Skill Requirements

Strong hands-on experience with RDF, RDFS, OWL, TTL, SHACL, SPARQL, and Semantic Web technologies.

• Practical knowledge of knowledge graphs, graph traversal, RDF stores, LPGs, and graph validation.
• Experience with schema-first and schema-late ontology development.
• Strong data modeling and reverse-engineering skills, including working with messy or incomplete source data.
• Experience with JSON Schema, relational data modeling, and mapping between relational/JSON and graph models.
• Strong Python skills for data processing, validation, and automation.
• Experience with graph databases such as GraphDB, Stardog, Neo4j, or similar.
• Experience with Git and CI/CD development practices.

Other Requirements

Master’s or PhD in Data Science, Computer Science, Artificial Intelligence, Knowledge Representation, Information Science, Engineering, or a related technical field preferred.

• Telecom / 5G & 4G network domain knowledge, including network functions, transport, inventory, configuration, and network relationships.
• Experience with Kubernetes and Helm configuration data.
• Experience with Ontology-RAG (O-RAG), GraphRAG, RAG, vector databases, and AI agent integration.
• Familiarity with MCP and agentic AI architectures.
• Experience with ontology design patterns such as SKOS and PROV-O.
• Familiarity with AI-assisted engineering tools such as Claude Code