Data Engineer (RAG & Retrieval) — SC Cleared, London

VIQU IT; City Of London; On-site; GBP 92,000 - 120,000; Full time

Job summary

Morela is recruiting a Data Engineer (RAG & Retrieval) for a 2-year contract in Central London, working on a UK government programme with an SC-cleared environment. You will own the data platform from ingestion to the retrieval layer powering AI capabilities, delivering robust pipelines and governance.

The role focuses on building RAG workflows, embeddings, and secure access controls, with hands-on experience in Python/SQL, cloud platforms and orchestration tools. Outside IR35 and rate TBC.

Qualifications

• Production data pipelines end-to-end across structured and unstructured data.
• Strong Python and SQL skills with data modelling, warehousing and lakehouse concepts.
• Experience with cloud data platforms (AWS/Azure/GCP) and containerised deployment (Docker, Kubernetes).
• Hands-on with orchestration and distributed processing (Airflow, Dagster, Spark).
• Experience with RAG, vector databases and retrieval pipelines.

Responsibilities

• Design, build and maintain robust batch and streaming ETL/ELT pipelines across sources.
• Model data for analytics with clear schemas, lineage and documentation.
• Own data quality, validation, monitoring and alerting for a trusted platform.
• Build RAG pipelines: embeddings, hybrid search, reranking, context assembly.
• Enforce document-level access controls and security in retrieval layers.
• Work with self-hosted or open-weight models in secure environments.

Skills

Python

SQL

Data modelling

Warehousing

Lakehouse

Airflow

Dagster

Spark

Cloud platforms

Containerisation

Tools

Kafka

OpenSearch

Qdrant

Weaviate

LangChain

Vector embeddings

Job description

Morela is recruiting a Data Engineer (RAG & Retrieval) for a 2-year contract in Central London, working on a UK government programme with an SC-cleared environment. You will own the data platform from ingestion to the retrieval layer powering AI capabilities, delivering robust pipelines and governance.

The role focuses on building RAG workflows, embeddings, and secure access controls, with hands-on experience in Python/SQL, cloud platforms and orchestration tools. Outside IR35 and rate TBC.