Data Engineer: Knowledge Graphs & AI-Ready Data Pipelines

McGregor Recruitment; Manchester; On-site; GBP 128,000 - 168,000; Full time

Job summary

McGregor Recruitment is recruiting a Data Engineer for a major Financial Services client. Location options include Bristol, Leeds, Manchester or Edinburgh, with an initial 3-month duration and potential extension.

The role focuses on building scalable data pipelines and knowledge solutions to support an Enterprise Knowledge Base. You will handle data ingestion, enrichment, indexing and knowledge graphs, transforming enterprise data into searchable, governed formats for AI consumption.

Qualifications

• Formal data engineering experience in a commercial setting.
• Strong Python and SQL capabilities.
• Experience with cloud data platforms such as BigQuery and Spanner.
• Hands-on Neo4j and Knowledge Graph experience.
• Experience with vector databases, search or indexing.
• Knowledge of data modelling, governance and lineage.
• Experience supporting AI/LLM/RAG use cases.

Responsibilities

• Build scalable ETL/ELT pipelines using Python and SQL.
• Work with BigQuery, Google Spanner, Neo4j and vector databases.
• Design and implement Knowledge Graphs.
• Develop enterprise search, indexing and retrieval capabilities.
• Build data models, metadata and enrichment processes.
• Implement event-driven and real-time data architectures.
• Ensure data quality, governance, lineage and traceability.
• Optimise platform performance and scalability.

Skills

Python

SQL

BigQuery

Spanner

Neo4j

Knowledge Graphs

Vector Databases

Search / Indexing

Data Modelling

Data Governance

AI / LLM / RAG

Job description

McGregor Recruitment is recruiting a Data Engineer for a major Financial Services client. Location options include Bristol, Leeds, Manchester or Edinburgh, with an initial 3-month duration and potential extension.

The role focuses on building scalable data pipelines and knowledge solutions to support an Enterprise Knowledge Base. You will handle data ingestion, enrichment, indexing and knowledge graphs, transforming enterprise data into searchable, governed formats for AI consumption.