7 of 7 Permanent Retrieval-Augmented Generation Jobs in Cardiff

Models (LLMs) to real-world challenges like email triage, document parsing, and data enrichment. Implement retrieval-augmented generation (RAG) to power internal AI assistants with trusted business knowledge. Rapidly prototype and iterate on Proofs of Concept to test ideas and gather user feedback early. … and vector databases. Familiarity with automation platforms like n8n, Zapier, or similar. Solid understanding of retrieval-augmented generation (RAG) methods. Strong problem-solving skills and the ability to design practical AI solutions with business outcomes in mind. Excellent communication skills – able to work cross More ❯

build and evolve Generative AI (GenAI) proof-of-concepts (POCs) for clients using techniques like Retrieval-Augmented Generation (RAG) and intelligent agents. Support the transition of these POCs into scalable, production-ready solutions. C Contribute to the design and development of full-stack applications More ❯

cross-functional teams. Experimental Approach: A passion for rapid iteration, learning from experiments, and data-driven development. Preferred Qualifications Experience designing RAG (Retrieval-Augmented Generation) or CAG systems using vector databases and hybrid retrieval techniques. Knowledge of LLM security challenges, including prompt More ❯

strategies - Designing robust API interfaces - Creating comprehensive testing frameworks 🟣 Client Solutions - Translating complex requirements into elegant technical solutions - Building custom knowledge graph applications - Implementing RAG systems with advanced reasoning capabilities - Delivering high-quality, maintainable code to clients What We're Looking For: 🔵 Technical Expertise - Strong Python skills with experience in More ❯

comparable) servers. Practical knowledge of Next.js and modern front-end tooling. Practical knowledge of Express . Deep understanding of core LLM concepts such as RAG pipelines, vector embeddings, fine-tuning methodologies, tokenization , and latency/throughput trade-offs. An understanding of the LLM model landscape and the strengths and weaknesses More ❯

looking for an experienced ML engineer to help build and scale GenAI features across real products. You’ll be hands-on with NLP pipelines, RAG systems, LLM deployment, and AI infrastructure, working closely with product and platform teams to turn ideas into features. It’s the kind of role where … your code ships and your input shapes the roadmap. 🚀 Expect work across: GenAI + LLM tooling (vLLM, LangChain, HuggingFace) RAG systems, embeddings, reranking NLP tasks like summarisation, classification, sentiment Scalable deployment in AWS (with support from DevOps) Cross-team collaboration and mentoring Why join? Own and build GenAI features that More ❯

platform is already trusted by nearly half of the top 50 financial institutions globally. 🧠 The Technology At the core of our platform is a RAG-based architecture , purpose-built for finance. It’s designed to replicate the kind of deep reasoning you see in leading models like OpenAI’s o1 … and can build production-ready systems end-to-end Are excited by AI-native product design and have experience working with or around LLMs, RAG, or agent-like architectures Love talking to users and solving real business problems—not just coding in a vacuum Bring an entrepreneurial mindset , with an More ❯