LLM Engineer – RAG & Knowledge Systems

About the role

We are seeking an LLM Engineer to design and implement retrieval‑augmented generation (RAG) systems that power next‑generation AI applications. You will work on intelligent assistants, AI copilots, and advanced search experiences that combine large language models, retrieval pipelines, and enterprise knowledge sources.

Key responsibilities

• Design and build RAG architectures and retrieval pipelines.
• Develop systems using LLMs, embeddings, and vector databases.
• Optimize relevance, latency, and response quality of AI services.
• Integrate AI capabilities into backend platforms and APIs.
• Create evaluation and testing frameworks for retrieval quality.
• Collaborate with AI, backend, and product teams to deliver production‑ready solutions.

Required profile

• 3+ years of experience in AI, backend, or machine‑learning engineering.
• Strong Python programming background.
• Hands‑on experience with LangChain, LlamaIndex, or similar frameworks.
• Proven work with vector databases such as Pinecone, Weaviate, FAISS, or ChromaDB.
• Understanding of embeddings, semantic search, and LLM workflows.
• Experience deploying AI systems into production environments.

Required skills

• Python
• LangChain
• LlamaIndex
• Pinecone
• Weaviate
• FAISS
• ChromaDB
• OpenAI APIs
• AWS
• Azure
• GCP

What we offer

• Work on cutting‑edge LLM and generative AI systems.
• Join a fast‑growing area of AI engineering.
• Onsite collaboration in London with hybrid flexibility.
• Opportunity to build AI solutions used in real‑world production environments.