Senior Knowledge Graph Engineer

NucleusTeq; Phoenix (AZ); On-site; USD 120,000 - 180,000; Full time

Job summary

NucleusTeq is seeking a Senior Knowledge Graph Engineer to design and scale an enterprise knowledge graph powering our search, analytics, and AI products. You will own ontology design, data modeling, and ingestion pipelines, delivering GraphRAG solutions that ground LLMs with structured context.

You will work with RDF/OWL/SHACL, Cypher, SPARQL, and graph databases, building scalable ETL pipelines, entity resolution, NLP-driven extraction, and graph analytics.

Qualifications

• Bachelor's or Master's degree in Computer Science, Information Science, Data Engineering, or a related field.
• 5+ years in data engineering or software engineering, with 3+ years building production knowledge graphs.
• Strong knowledge of semantic web standards: RDF, OWL, SPARQL, and SHACL.
• Hands-on experience with property graph databases and Cypher or Gremlin.
• Proficiency in Python, plus Java or Scala.
• Ontology modeling experience with tools such as Protégé, TopBraid, or PoolParty.
• Experience with data pipelines using Apache Spark, Kafka, Airflow, or dbt.
• Solid grasp of data modeling, schema design, and query optimization.
• Experience with cloud platforms such as AWS, Azure, or GCP.

Responsibilities

• Design and maintain ontologies, taxonomies, and semantic data models using RDF, RDFS, OWL, and SKOS.
• Build and optimize knowledge graphs on platforms such as Neo4j, Amazon Neptune, Stardog, GraphDB, or TigerGraph.
• Develop scalable ETL/ELT pipelines to ingest data into the graph.
• Implement entity resolution, entity linking, and deduplication across heterogeneous data sources.
• Extract entities and relationships from text using NLP and LLMs, including named entity recognition (NER), relation extraction, and schema-guided extraction.
• Build GraphRAG and hybrid retrieval systems that combine graph traversal, vector search, and LLMs.
• Write and tune complex SPARQL, Cypher, and Gremlin queries for performance at scale.
• Enforce data quality and graph validation with SHACL constraints and automated testing.
• Apply graph analytics and machine learning: centrality, community detection, link prediction, node embeddings, and graph neural networks (GNNs).
• Expose graph data through APIs such as GraphQL, REST, and SPARQL endpoints for downstream applications.
• Work with data scientists, product managers, and domain experts to model business concepts and use cases.
• Set graph governance standards, including versioning, provenance, lineage, and access control.
• Mentor junior engineers and advocate for semantic technology best practices.

Skills

Knowledge graphs

Data engineering

Python

SPARQL

Cypher

Gremlin

OWL/RDF/SHACL

NLP/LLMs

Cloud platforms

Java/Scala

Education

Bachelor's or Master's in CS/IS/DE

Tools

Protégé

TopBraid

PoolParty

Apache Spark

Kafka

Airflow

dbt

Job description

We're looking for a Senior Knowledge Graph Engineer to design, build, and scale the enterprise knowledge graph behind our search, analytics, and AI products. You'll turn scattered data into connected knowledge. You'll own the path from ontology design through ingestion pipelines to GraphRAG applications that feed large language models (LLMs) with grounded context.

Key responsibilities

• Design and maintain ontologies, taxonomies, and semantic data models using RDF, RDFS, OWL, and SKOS.
• Build and optimize knowledge graphs on platforms such as Neo4j, Amazon Neptune, Stardog, GraphDB, or TigerGraph.
• Develop scalable ETL/ELT pipelines to ingest structured, semi-structured, and unstructured data into the graph.
• Implement entity resolution, entity linking, and deduplication across heterogeneous data sources.
• Extract entities and relationships from text using NLP and LLMs, including named entity recognition (NER), relation extraction, and schema-guided extraction.
• Build GraphRAG and hybrid retrieval systems that combine graph traversal, vector search, and LLMs.
• Write and tune complex SPARQL, Cypher, and Gremlin queries for performance at scale.
• Enforce data quality and graph validation with SHACL constraints and automated testing.
• Apply graph analytics and machine learning: centrality, community detection, link prediction, node embeddings, and graph neural networks (GNNs).
• Expose graph data through APIs such as GraphQL, REST, and SPARQL endpoints for downstream applications.
• Work with data scientists, product managers, and domain experts to model business concepts and use cases.
• Set graph governance standards, including versioning, provenance, lineage, and access control.
• Mentor junior engineers and advocate for semantic technology best practices.

Required qualifications

• Bachelor's or Master's degree in Computer Science, Information Science, Data Engineering, or a related field.
• 5+ years in data engineering or software engineering, with 3+ years building production knowledge graphs.
• Strong knowledge of semantic web standards: RDF, OWL, SPARQL, and SHACL.
• Hands-on experience with property graph databases and Cypher or Gremlin.
• Proficiency in Python, plus Java or Scala.
• Ontology modeling experience with tools such as Protégé, TopBraid, or PoolParty.
• Experience with data pipelines using Apache Spark, Kafka, Airflow, or dbt.
• Solid grasp of data modeling, schema design, and query optimization.
• Experience with cloud platforms such as AWS, Azure, or GCP.

Preferred qualifications

• Experience with LLM frameworks such as LangChain or LlamaIndex, and with GraphRAG architectures.
• Familiarity with vector databases such as Pinecone, Weaviate, or pgvector, and with embedding models.
• Knowledge of graph ML libraries such as PyTorch Geometric, DGL, or Neo4j Graph Data Science.
• Exposure to industry ontologies such as FIBO, schema.org, SNOMED CT, or Gene Ontology.
• Experience with master data management (MDM) or data catalogs such as Collibra or Alation.
• Neo4j Certified Professional or equivalent certification.
• Publications or open-source contributions in semantic technologies.
• Able to turn ambiguous business questions into clear semantic models.
• Communicates well with both technical and non-technical stakeholders.
• Thinks in systems and pays close attention to data quality.