3 of 3 Retrieval-Augmented Generation Jobs in Cambridge

Language Models (LLMs) and understanding of trade-offs between performance, cost, and capability. Understanding of Retrieval-Augmented Generation (RAG), agent orchestration, prompt engineering, and tool calling. Familiarity with AI standards such as Model Context Protocol (MCP) and Agent2Agent (A2A). Familiar with AI orchestration ...

rather than purely research-focused individuals. You will work on a broad range of AI challenges spanning multimodal AI, machine learning, computer vision, LLMs, RAG architectures, transformer models, audio processing and intelligent automation features within a highly collaborative engineering environment. Location: Cambridge, UK. Hybrid working model - minimum of 4 days … Kotlin, TypeScript and React, prior experience with these technologies is not required Interest and exposure across AI technologies such as machine learning, LLMs, RAG systems, computer vision, multimodal AI or transformer architectures Ability to work across both research/prototyping and production engineering Strong problem-solving ability and analytical thinking ...

value (and where it doesn’t) Use, advise on, and develop AI‐related features such as: Intelligent search/retrieval experiences and RAG Summarisation and document comprehension at scale Context management AI agents, MCP servers, and best‐practice configuration of, for example, AGENTS.md Advanced use of tools such … refactoring support, documentation acceleration, internal workflows) Building products that incorporate AI/LLM features (e.g. assistants/coplots, summarisation, document understanding, semantic search/RAG, extraction, classification, decision support, workflow automation) Strong engineering fundamentals You build with the discipline needed to keep software reliable and maintainable, including: automated testing strategies ...