Knowledge Graph Engineer for AI Data Pipelines & RAG

Gazelle Global; Greater London; Hybrid; GBP 70,000 - 105,000; Full time

Job summary

Gazelle Global seeks a Knowledge Engineer to build and operate data pipelines that populate the CDS knowledge graph at scale. You will transform structured and unstructured source data into governed knowledge assets, aligned with the Knowledge Modeller's schema to support retrieval and agent-based AI capabilities.

You will develop Python-based data engineering and ETL processes, define chunking and vector embedding strategies for RAG, and ensure data quality, freshness and lineage across the

Qualifications

• Hands-on experience building and populating knowledge graphs programmatically.
• Strong Python data engineering experience, including ingestion and ETL at scale.
• Experience with structured and unstructured data sources.
• Exposure to regulated or government environments.

Responsibilities

• Build and operate data pipelines that populate CDS knowledge graph at scale.
• Transform data into governed, high-quality knowledge assets per schema.
• Define chunking and vector embedding strategies for retrieval.
• Collaborate with AI engineers to support RAG and agent-based use cases.
• Maintain data quality, freshness and lineage of the knowledge graph.

Skills

Neo4j/Cypher

Python

ETL pipelines

Knowledge graphs

RAG

LangGraph

Tools

Neo4j/Cypher

RDF/SPARQL

OpenSearch

AWS Bedrock

LangGraph

Job description

Gazelle Global seeks a Knowledge Engineer to build and operate data pipelines that populate the CDS knowledge graph at scale. You will transform structured and unstructured source data into governed knowledge assets, aligned with the Knowledge Modeller's schema to support retrieval and agent-based AI capabilities.

You will develop Python-based data engineering and ETL processes, define chunking and vector embedding strategies for RAG, and ensure data quality, freshness and lineage across the