Knowledge Graph & Ontology Engineer (AI Knowledge Representation)
Role details
Job location
Tech stack
Job description
We are seeking an experienced Knowledge Graph & Ontology Engineer to design, implement, and govern the knowledge representation layer for next-generation AI systems. This role builds the foundational knowledge structures-ontologies, semantic models, knowledge graphs, provenance, and data fusion patterns-that enable AI agents and LLM applications to reason over enterprise knowledge reliably. You will collaborate closely with Retrieval/Relevance engineering, AI researchers, and data engineering to ensure our knowledge is well-structured, consistent, explainable, and evolvable., * Develop and maintain ontologies, knowledge graphs, and semantic data models to structure and integrate domain knowledge for improved reasoning and downstream retrieval.
- Define canonical entities, relationships, attributes, and constraints, including taxonomy/controlled vocabularies and semantic definitions.
- Establish schema versioning, governance, and backward compatibility strategies to evolve the knowledge model safely.
Data Fusion & Knowledge Integration
- Aggregate disparate knowledge bases and heterogeneous data into a fused, consistent representation with clear semantics and lineage.
- Design integration patterns for structured + unstructured sources (e.g., documents entities/relations) and maintain alignment across domains.
Provenance, Lineage, and Data Quality
- Define and enforce provenance/lineage standards (source attribution, timestamps, confidence, auditability).
- Collaborate with pipeline engineers to implement validation rules and quality gates for knowledge graph construction (e.g., integrity constraints, anomaly detection).
- Cognitive Memory & Persistent Knowledge Structures (Representation View)
- Design representation primitives that support cognitive memory architectures for AI agents (identity, episodic traces, persistent facts, context scoping).
Collaboration & Documentation
- Partner with Retrieval/Relevance engineering to define metadata contracts and "safe traversal" semantics for graph-aware retrieval.
- Maintain clear documentation of schemas, ontologies, knowledge modeling guidelines, and governance processes.
- Evaluate and integrate new technologies and research in knowledge representation and semantic modeling.
Requirements
Do you have experience in Semantic Web?, Do you have a Master's degree?, * Bachelor's or Master's degree in Computer Science, Data Science, Machine Learning, or related field (or equivalent experience).
- Proven experience building knowledge graphs, semantic data models, and/or enterprise knowledge bases.
- Experience with semantic technologies and standards (as applicable): RDF, OWL, SPARQL (or equivalent graph/ontology concepts).
- Strong foundations in data modeling, entity resolution/canonicalization, and schema governance.
- Proficiency in Python and working with data pipelines (in collaboration with data engineering).
- Excellent analytical, problem-solving, and cross-functional communication skills.
Nice To Haves
- Experience designing agent memory representations (episodic/semantic memory patterns, long-term context).
- Familiarity with LLM grounding patterns (provenance, citations, trust signals).
- Experience with graph databases and tooling (e.g., Neo4j/AWS Neptune equivalents).
- Experience with data-centric AI and training data quality assessment.
Primary Ownership (What success looks like)
- The knowledge model is correct, consistent, explainable, and governable.
- High-quality entity resolution + clean relationships + strong provenance coverage.
- Stable schemas that evolve without breaking downstream applications.