About the role
Responsibilities:
- Design and build the production knowledge graph platform: data models, ontology standards, and infrastructure.
- Build knowledge graphs representing educational content, skills taxonomies, learner models, and curriculum structures.
- Enable GraphRAG architectures integrating knowledge graphs with LLM retrieval pipelines for contextual AI responses.
- Define ontology governance standards, schema versioning, and knowledge base quality assurance processes.
- Optimize graph database performance: query tuning, index design, partitioning, and scaling strategies.
- Build entity resolution and knowledge base construction pipelines from heterogeneous data sources.
- Design semantic search capabilities combining graph-native and vector-based hybrid retrieval approaches.
- Collaborate with ML teams on graph-native features: recommendation, adaptive learning paths, and gap detection.
- Evaluate and evolve the graph technology stack as platform and data complexity scales.
- Define and enforce data quality standards for the knowledge graph: completeness checks, consistency validation, and remediation workflows.
- Drive graph-based data integration across heterogeneous sources and establish reasoning pipelines for semantic AI applications.
Requirements:
- Strong experience in designing and managing graph database solutions in production environments.
- Deep understanding of knowledge graphs, ontologies, and graph data modeling.
- Hands-on experience with Neo4j, JanusGraph, Apache Jena, or similar graph databases.
- Strong knowledge of RDF, property graphs, SPARQL, and Cypher query languages.
- Experience building and maintaining large-scale domain ontologies and knowledge graphs.
- Understanding of ontology governance, versioning, and data quality standards.
- Experience with graph-based data integration, reasoning, and semantic technologies.
- Strong problem-solving skills and ability to design scalable graph data architectures.