Artificial Intelligence Engineer

Prism Digital

LLM EngineerjuniorLondon Area, United KingdomhybridfulltimeResearch ServicesPythonSQLLLMsRAGLangGraphDockerGitAWSposted 28 Jul
Unlock apply linkApply links and the original listing are a Pro feature: £4.99/mo or £25 once.
AI Engineer | Python, SQL, LLMs \& RAG | Fast-Growing London Intelligence Firm * Location: Central London, primarily office-based (4 days per week on-site) You will be building the AI systems a research business actually runs on: retrieval-augmented generation (RAG) pipelines, agent workflows, and the data products that feed them. This is an engineering seat where you sit alongside senior engineers, take well-defined tasks through to production, and watch your work get used by research, product and member-facing teams instead of parked in a prototype folder. The company is a fast-growing, membership-based intelligence firm in central London. It serves senior operations and supply chain leaders at some of the world’s biggest brands with research, advisory, data and a peer community. The engineering team is small and scaling, so you get proper mentoring and a lot of surface area early. This is a primarily office-based role, four days a week on-site, so it fits someone who wants to learn fast in the room with the team rather than remotely. It suits someone two or three years in who has taken things through to production and now wants to go deep on LLM-based systems: RAG, agents, evaluation, and the data plumbing underneath. You will own well-defined pieces, debug live systems, document what you build, and translate what non-technical teams need into working code. What They’re Looking For: * 2-3 years in software, data, ML or AI engineering, with examples taken through to production * Python (strong) * SQL (strong) * Software deployed and running in production cloud environments * Large language models (LLMs), AI APIs or open-source models used to build applications * Cloud platform (AWS or Google Cloud) * Eligible to work in the UK * Able to be on-site in central London four days a week What You’ll Work With: * RAG pipelines (chunking, embeddings, metadata tagging, retrieval quality) * Agent workflows and frameworks (LangGraph) * Data pipelines: preparing, cleaning, transforming and validating datasets * API development and integrations * Containerisation (Docker) * CI/CD and version control (Git) Nice to Haves: * Master’s in Data Science, Data Engineering or AI * AI evaluation experience (prompt tests, regression checks, quality measurement) * Supply chain or operations domain knowledge * Worked cross-functionally with research, product or commercial teams Why Join? Most engineers this early get handed narrow tickets and little context. Here you get the opposite: production ownership from the start, senior engineers next to you to learn from, and breadth across RAG, agents, data pipelines and internal tooling rather than one corner of a stack. Because the team is scaling, the standards, documentation and processes are still being set, so you help shape how the team works as it grows, not just inherit it. Your work lands in front of research, product and member-facing teams serving major global brands, so you see the impact quickly. If you like agentic AI and emerging LLM architectures and want to build serious experience with production systems, this is a strong place to do it. Employee Benefits * Unlimited holiday * Private healthcare and life insurance * Enhanced pension * Enhanced parental leave * Custom-designed offices with free breakfast and snacks If this sounds like your kind of role, apply and I’ll give you a call to talk through the detail. AI Engineer | Python, SQL, LLMs \& RAG | Fast-Growing London Intelligence Firm