RAG Engineer

Location: UK (Remote/Hybrid)

Salary: £80,000 – £120,000 + Benefits (DOE)

We're looking for an experienced RAG Engineer to help design and build enterprise-grade AI applications powered by Large Language Models.

This is an opportunity to work on cutting-edge Generative AI solutions, building intelligent systems that combine LLMs with retrieval pipelines to deliver accurate, secure and scalable AI products.

• Design and build Retrieval-Augmented Generation (RAG) architectures.
• Develop production-ready AI applications using modern LLM frameworks.
• Optimise vector search and embedding strategies.
• Build ingestion pipelines for structured and unstructured data.
• Engineer prompts, evaluation frameworks and AI guardrails.
• Integrate LLMs with enterprise APIs, databases and knowledge bases.
• Work closely with ML Engineers, Software Engineers and Product teams to deploy AI solutions at scale.

• Commercial experience building RAG-based AI applications.
• Strong Python development skills.
• Experience with Lang Chain, Llama Index or similar frameworks.
• Knowledge of vector databases such as Pinecone, Weaviate, Milvus or Chroma.
• Experience with embedding models and semantic search.
• Familiarity with OpenAI, Anthropic, Google Gemini or open-source LLMs.
• Understanding of prompt engineering, AI evaluation and hallucination mitigation.
• Experience deploying AI applications using Azure, AWS or GCP.
• Excellent communication skills and a passion for building production AI systems.

• Experience with AI agents and multi-agent architectures.
• Knowledge of Kubernetes and Docker.
• Experience with CI/CD pipelines.
• Exposure to GraphRAG, knowledge graphs or hybrid search.
• Understanding of AI governance, security and responsible AI.

• Work on genuinely innovative AI products.
• Competitive salary and bonus.
• Flexible remote/hybrid working.
• Personal development budget.
• Opportunity to influence the future direction of enterprise AI.