LLM Engineer
LLM Engineer – RAG & Knowledge Systems
Onsite (London, UK) | Hybrid Option Available
Experience: 3+ years
AI | Generative AI | Knowledge Systems
About the Role
We’re looking for an LLM Engineer to design and implement retrieval-augmented generation (RAG) systems powering next-generation AI applications.
You’ll work on intelligent systems that combine large language models, retrieval pipelines, and enterprise knowledge sources to create AI copilots, assistants, and advanced search experiences used in real-world environments.
This role is ideal for engineers who enjoy working on the cutting edge of:
- generative AI
- semantic search
- retrieval systems
- and production-grade LLM applications.
What You’ll Be Working On
- AI copilots and intelligent assistants
- Enterprise knowledge and document systems
- Retrieval pipelines combining:
- embeddings
- vector databases
- LLM inference
- Production-grade generative AI workflows
Key Responsibilities
- Design and implement RAG architectures and retrieval pipelines
- Develop systems using LLMs, embeddings, and vector databases
- Optimise relevance, latency, and response quality of AI systems
- Integrate AI services into backend platforms and APIs
- Build evaluation and testing frameworks for retrieval quality
- Collaborate with AI, backend, and product teams to deliver production-ready systems
Required Skills & Experience
- 3+ years experience in AI, backend, or machine learning engineering
- Strong Python programming skills
- Experience with LangChain, LlamaIndex, or similar frameworks
- Experience working with vector databases (Pinecone, Weaviate, FAISS, ChromaDB, etc.)
- Understanding of embeddings, semantic search, and LLM workflows
- Experience building or deploying AI systems into production
Nice to Have
- Experience with OpenAI APIs or open-source LLMs
- Familiarity with prompt engineering and context optimisation
- Experience with cloud platforms (AWS, Azure, or GCP)
- Exposure to knowledge management or enterprise AI systems
Why Join?
- Work on cutting-edge LLM and generative AI systems
- Be part of one of the fastest-growing areas in AI engineering
- Onsite collaboration in London with hybrid flexibility
- Opportunity to build AI systems used in real-world production environments
If you’re passionate about LLMs, semantic retrieval, and building intelligent AI systems, we’d love to hear from you.
Apply via XpertDirect — connecting companies with advanced AI engineering talent.