Data Engineer - SQL/Python

Job Description:

We are seeking a highly experienced Senior Data Engineer (1015 years) to design and scale AI-ready, compliant data platforms with a strong focus on Retrieval-Augmented Generation (RAG) architectures.

This role is critical in enabling secure, governed, and explainable AI solutions in a regulated financial services environment, ensuring compliance with data privacy, model governance, and audit requirements.

The ideal candidate combines deep data engineering expertise, GenAI experience, and strong understanding of regulatory and risk frameworks.

Required Skills & Experience:

- 1015 years in Data Engineering / Platform Engineering

- 3+ years in GenAI / RAG / LLM-based systems

- Proven experience working in regulated environments (Banking, Insurance, or similar)

Core Technical Skills:

- Strong expertise in:

1. Python, SQL

2. Data modelling, ETL/ELT pipelines

3. Distributed data systems

- Deep AWS experience:

1. S3, Glue, Lambda, EMR, Redshift, Kinesis, IAM

- Data orchestration tools:

1. Airflow / Step Functions

RAG & GenAI:

- Hands-on experience building:

1. Enterprise RAG pipelines with governed data access

2. Vector databases (OpenSearch, Pinecone, FAISS, Chroma)

- Strong understanding of:

1. Embeddings, semantic search

2. Chunking strategies & retrieval optimisation

- Experience with:

1. LangChain, LlamaIndex (or equivalent)

Regulatory & Governance Expertise (Must-Have):

- Strong knowledge of:

1. GDPR / UK Data Protection Act

2. Data governance frameworks (data classification, lineage, retention)

3. Access control models (RBAC, ABAC)

- Experience implementing:

1. Data masking, anonymisation

2. Encryption & key management

3. Audit trails and compliance reporting

- Familiarity with:

1. Model Risk Management frameworks

2. Responsible AI principles (fairness, transparency, accountability)

Preferred / Advanced Skills:

- Experience with:

1. Graph databases (Neo4j, Neptune) for Graph RAG

2. Agent orchestration frameworks

- Knowledge of:

1. LLM evaluation frameworks

2. Guardrails, safety filters, red-teaming

- Exposure to:

1. API-first, microservices architecture

2. Customer-facing AI journeys (chatbots, knowledge assistants)

Skills

Python, SQL, Data Engineering, AWS, RAG, LLM, Data Modeling, ETL, Data Pipeline