Senior AI Data Engineer

Overview

In this role you will implement Comply’s semantic layer, turning ontological models into production-ready knowledge graphs, vector search infrastructure, and LLM-powered pipelines. You’ll own semantic layer delivery and collaborate with application and data teams to ensure AI-ready data products are reliable and scalable. You’ll join a new Data and Analytics team to advance our AI ambitions and enable future data capabilities in the compliance domain. This role offers hands-on work at the intersection of knowledge representation and AI infrastructure with meaningful impact on regulatory programs.

Responsibilities

• Implement JSON-LD semantic models into production data systems
• Build and maintain knowledge graph structures and graph DB schemas
• Develop data ingestion pipelines and ensure semantic consistency with downstream products
• Design embedding pipelines and operate vector DB infrastructure for semantic search
• Implement RAG architectures grounding LLM outputs in proprietary data
• Evaluate and integrate suitable LLM tooling and frameworks
• Build reliable, observable data pipelines from upstream sources
• Apply DataOps practices including testing, monitoring, lineage, and SLAs
• Collaborate with Ontologist to reflect domain intent in models
• Assist application teams in adopting AI-ready data products

Key requirements

• Strong hands-on data engineering with a focus on semantic or AI data infrastructure
• Experience building/operating knowledge graphs or graph databases (e.g. Jena Fuseki, Neo4j, Amazon Neptune)
• Experience with vector databases and embedding pipelines (e.g. Pinecone, Weaviate, Qdrant, pgvector)
• Practical experience implementing RAG architectures or LLM-integrated data pipelines
• Familiarity with semantic web standards — JSON-LD, RDF, OWL, SKOS
• Strong Python skills and data pipeline framework experience
• Experience with cloud-native data platforms (AWS, Azure, or GCP)
• Desirable: domain-driven design (DDD) and bounded contexts
• Experience working with ontologists or knowledge engineers is a plus
• Familiarity with data contracts and data product frameworks is a plus
• Experience with DataOps tooling, data reliability, or data observability is desirable
• Background in financial services, RegTech, or compliance data is a plus

• Cross-functional collaboration
• Strong communication with technical and non-technical stakeholders
• Problem-solving mindset with attention to data quality
• JSON-LD, RDF, OWL, SKOS
• Graph databases: Jena Fuseki, Neo4j, Amazon Neptune
• Vector databases: Pinecone, Weaviate, Qdrant, pgvector