Senior AI EngineerIn office ~x2 days a weekThis is a newly created opportunity to join a well-established data organisation that is investing in advanced AI capabilities to enhance data intelligence, automate research processes, and bring new value to their users. The team is building out scalable AI systems from the ground up, combining deep software engineering rigour with cutting-edge machine learning and retrieval techniques.You will work at the intersection of data engineering, AI product development, and platform reliability. This role suits someone who enjoys building robust pipelines, working on modern LLM integrations, and applying AI tools to real-world knowledge domains.What You’ll Be DoingBuild and manage data ingestion pipelines capable of processing various document types, including text files, spreadsheets, structured JSON, and audio sourcesDesign intelligent retrieval systems that combine structured chunking, advanced indexing, re-ranking methods, and hybrid search approachesDevelop machine learning and LLM-based applications for tasks like information extraction, document classification, summarisation, and semantic queryingConstruct and maintain multi-step LLM workflows using tools such as LangChain, LangGraph, or similar frameworks that support tool usage and agent coordinationHelp define internal testing and validation processes to assess model accuracy, factuality, and relevanceCollaborate closely with product, engineering, and data teams to embed AI capabilities into user-facing platformsDeploy solutions in an Azure-based cloud environment, using container orchestration, automation pipelines, secure key management, and observability toolingEnforce data security and responsible AI practices, including anonymisation, access control, and model auditabilityWhat They’re Looking ForHands-on experience delivering production-ready AI or LLM solutions, ideally with 2+ years working in a similar roleStrong Python development background and confidence using popular machine learning libraries such as PyTorch, TensorFlow, or scikit-learnFamiliarity with vector-based storage and search systems (e.g. pgvector, Pinecone, Azure Search), as well as experience working with graph technologies like Neo4jPractical understanding of retrieval-augmented generation pipelines and how to implement structured outputs or link models to graph-based knowledge systemsTrack record of optimising and scaling AI systems to handle real-world loads with high reliabilityKnowledge of modern ML/LLM deployment workflows, including testing, infrastructure automation, and version controlExposure to frontend integration, particularly with frameworks like Angular, is a nice bonusAny experience in content-heavy industries such as publishing, research, or legal analytics is welcome but not requiredStrong communication skills with the ability to work across teams and clearly articulate complex technical ideas to a variety of audiencesIf this role interests you and you would like to find out more (or find out about other roles), please apply here or contact us via niall.wharton@Xcede.com (feel free to include a CV for review).