Senior AI Data Engineer: Knowledge Graphs & Vector AI

Comply; York and North Yorkshire; On-site; GBP 90,000 - 130,000; Full time

Job summary

Comply in York, UK, is seeking a Senior AI Data Engineer to turn semantic data models into knowledge graphs and AI-ready pipelines. You’ll own semantic layer components and collaborate with data engineers, architects, and an ontologist to ensure scalable, reliable AI-enabled data products.

This role focuses on production-grade JSON-LD semantics, vector embedding, RAG, and graph databases, with cloud-native platforms and DataOps practices.

Qualifications

• Extensive hands-on data engineering experience in semantic or AI data infrastructure.
• Experience building and operating knowledge graphs or graph databases.
• Proficiency with vector databases and embedding pipelines.
• Practical experience implementing RAG architectures or LLM-integrated data pipelines.
• Familiarity with JSON-LD, RDF, OWL, or SKOS standards.
• Strong Python skills and data pipeline frameworks.
• Experience with AWS, Azure, or GCP.

Responsibilities

• Implement JSON-LD semantic models from the ontologist into production data systems.
• Develop graph database schemas, queries, and ingestion pipelines while maintaining semantic consistency.
• Design embedding pipelines and store representations in vector space.
• Build and operate vector DB infrastructure for semantic search and retrieval.
• Implement RAG architectures and integrate LLM tooling for use cases.
• Create observable data pipelines with testing, monitoring, and lineage tracking.
• Collaborate with data/backend teams to embed semantic models into APIs and contracts.
• Work with the ontologist to ensure domain intent is reflected in models.

Skills

Data engineering

Knowledge graphs

Graph databases

Vector databases

Embedding pipelines

RAG architectures

LLM data pipelines

JSON-LD

RDF/OWL/SKOS

Python

Cloud platforms

Tools

Neo4j

Jena Fuseki

Amazon Neptune

Pinecone

Weaviate

Qdrant

pgvector

Job description

Comply in York, UK, is seeking a Senior AI Data Engineer to turn semantic data models into knowledge graphs and AI-ready pipelines. You’ll own semantic layer components and collaborate with data engineers, architects, and an ontologist to ensure scalable, reliable AI-enabled data products.

This role focuses on production-grade JSON-LD semantics, vector embedding, RAG, and graph databases, with cloud-native platforms and DataOps practices.