We are seeking a highly experienced Senior Data Engineer (10 to 15 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.
Roles & Responsibilities:
- Build and maintain data pipelines and data models.
- Develop enterprise RAG solutions with secure data access.
- Design and manage data workflows using AWS services.
- Implement data governance, security, and compliance requirements.
- Work with development teams to build AI-powered applications.
- Monitor and improve data quality, performance, and reliability.
Must Have Skills:
- Python and SQL
- Data modelling and ETL/ELT pipelines
- Distributed data systems
- AWS: S3, Glue, Lambda, EMR, Redshift, Kinesis, IAM
- Airflow or AWS Step Functions
- Enterprise RAG implementation
- Vector databases (OpenSearch, Pinecone, FAISS, or Chroma)
- Embeddings, semantic search, chunking, and retrieval optimization
- LangChain, LlamaIndex, or similar frameworks
- Knowledge of GDPR, UK Data Protection Act, and data governance
- RBAC/ABAC, data masking, encryption, audit logging, and compliance reporting
- Responsible AI principles and Model Risk Management
Good to Have Skills:
- Graph databases (Neo4j or Neptune)
- Graph RAG
- Agent orchestration frameworks
- LLM evaluation frameworks
- Guardrails, safety filters, and red-teaming
- API-first and microservices architecture
- Customer-facing AI applications such as chatbots and knowledge assistants
Nasugroup