LLM Engineer – Retrieval & Knowledge Systems

Remote (London, UK – Hybrid Option Available)

AI | LLMs | Knowledge Systems

About the Role

We’re looking for an LLM Engineer to design and deploy retrieval-augmented generation (RAG) systems powering intelligent applications used in enterprise and research environments.

This role goes beyond prompt engineering — you’ll work on end-to-end LLM systems, including retrieval pipelines, embeddings, and scalable inference.

Key Responsibilities

• Design and implement RAG architectures (retrieval + generation pipelines)
• Work with vector databases and embedding models
• Optimise LLM performance, latency, and cost
• Build evaluation frameworks for model quality and relevance
• Integrate LLM systems into production environments

Required Skills & Experience

• 4+ years in AI / ML engineering
• Strong Python
• Experience with LLMs and generative AI systems
• Experience with vector databases (Pinecone, Weaviate, FAISS, etc.)
• Experience building production AI systems

Nice to Have

• Experience with LangChain / LlamaIndex or similar frameworks
• Knowledge of fine-tuning or prompt optimisation strategies
• Experience with large-scale document or knowledge systems

Why Join?

• Work on state-of-the-art LLM systems in production
• High ownership in a rapidly evolving AI domain
• Hybrid flexibility in a major AI hub (London)