51 to 75 of 304 Retrieval-Augmented Generation Jobs in the UK

Master prompt engineering, learning how to craft effective prompts for controlling AI outputs. Step 9 – Retrieval-Augmented Generation (RAG) Learn how to integrate external knowledge into AI systems using RAG techniques and vector databases. Step 10 – AI Specialised Customer Service Chatbot Project Combine prompt … engineering and RAG to build an AI-powered customer service chatbot, delivering intelligent responses using vector databases and knowledge bases. Step 11 – Machine Learning Fundamentals Understand machine learning principles and algorithms, and how to train and test models using scikit-learn. Step 12 – Machine Learning Project Put your machine learning ...

Master prompt engineering, learning how to craft effective prompts for controlling AI outputs. Step 9 – Retrieval-Augmented Generation (RAG) Learn how to integrate external knowledge into AI systems using RAG techniques and vector databases. Step 10 – AI Specialised Customer Service Chatbot Project Combine prompt … engineering and RAG to build an AI-powered customer service chatbot, delivering intelligent responses using vector databases and knowledge bases. Step 11 – Machine Learning Fundamentals Understand machine learning principles and algorithms, and how to train and test models using scikit-learn. Step 12 – Machine Learning Project Put your machine learning ...

Master prompt engineering, learning how to craft effective prompts for controlling AI outputs. Step 9 – Retrieval-Augmented Generation (RAG) Learn how to integrate external knowledge into AI systems using RAG techniques and vector databases. Step 10 – AI Specialised Customer Service Chatbot Project Combine prompt … engineering and RAG to build an AI-powered customer service chatbot, delivering intelligent responses using vector databases and knowledge bases. Step 11 – Machine Learning Fundamentals Understand machine learning principles and algorithms, and how to train and test models using scikit-learn. Step 12 – Machine Learning Project Put your machine learning ...

Master prompt engineering, learning how to craft effective prompts for controlling AI outputs. Step 9 – Retrieval-Augmented Generation (RAG) Learn how to integrate external knowledge into AI systems using RAG techniques and vector databases. Step 10 – AI Specialised Customer Service Chatbot Project Combine prompt … engineering and RAG to build an AI-powered customer service chatbot, delivering intelligent responses using vector databases and knowledge bases. Step 11 – Machine Learning Fundamentals Understand machine learning principles and algorithms, and how to train and test models using scikit-learn. Step 12 – Machine Learning Project Put your machine learning ...

Master prompt engineering, learning how to craft effective prompts for controlling AI outputs. Step 9 – Retrieval-Augmented Generation (RAG) Learn how to integrate external knowledge into AI systems using RAG techniques and vector databases. Step 10 – AI Specialised Customer Service Chatbot Project Combine prompt … engineering and RAG to build an AI-powered customer service chatbot, delivering intelligent responses using vector databases and knowledge bases. Step 11 – Machine Learning Fundamentals Understand machine learning principles and algorithms, and how to train and test models using scikit-learn. Step 12 – Machine Learning Project Put your machine learning ...

world impact. This position sits within a growing AI function and will focus heavily on Retrieval-Augmented Generation (RAG), agentic workflows, evaluation frameworks, and LLM optimisation. Key Responsibilities: Design and develop scalable RAG pipelines and generative AI workflows Build solutions using LangChain, LangGraph … contribute to technical best practices Key Requirements: Strong Python engineering experience Commercial experience building production-grade AI/ML systems Hands-on experience with RAG architectures and LLM workflows Experience with LangChain, LangGraph, and/or Llama Index Understanding of evaluation methodologies for generative AI Experience working within scalable cloud ...

optimise Python-based AI components, including prompt orchestration, output validation, and evaluation tooling. Work with Generative and Agentic AI patterns, including LLM integration, RAG architectures, prompt-driven workflows, and AI service orchestration. Integrate AI capabilities with enterprise systems, observability tooling, and security frameworks. Design and maintain CI/CD pipelines … within cloud-native engineering environments. Support benchmarking, evaluation, experimentation, and cost optimisation for LLM workloads. Contribute to scalable RAG implementations and enterprise data access patterns. Help define reusable APIs, engineering standards, and platform documentation. Troubleshoot and optimise distributed systems and cloud-based services. Collaborate across engineering, platform, architecture, and product ...

solutions. Key responsibilities include: Building and deploying Machine Learning and LLM-powered applications Developing Retrieval-Augmented Generation (RAG) solutions Evaluating model performance and addressing failure modes Testing, troubleshooting and improving AI systems Working closely with software and data engineering teams Helping drive engineering best ...

emerging AI/ML capabilities within modern data platforms. Exposure to vector databases, embeddings, retrieval-augmented generation (RAG), and AI-ready data architectures. Retail, wholesale, supply chain, or large-scale transactional data experience. ...

drive enterprise opportunities from qualification to close. Develop and maintain a strong perspective on how AI – including large language models, agentic architectures, and RAG-based solutions – can drive measurable business value across verticals and functions. Understand customer pain points in adopting and implementing AI solutions, and position Uniphore … trusted partner to address them. Deliver compelling technical presentations and demos showcasing GenAI, Agentic AI, RAG, and LLM-based capabilities tailored to each prospect’s context. Build and deliver custom demos and proof-of-concepts (POCs) to validate business value and technical feasibility. Conduct discovery sessions with key business ...

hands-on with Python and Azure , possessing a proven track record of designing and deploying Retrieval-Augmented Generation (RAG) patterns. Key Responsibilities Architect & Govern: Design and implement robust on-premises, cloud, and hybrid AI solutions, ensuring strict technical governance and best practices across … client relationships to secure consensus on complex technical architectures. Essential Skills Clearance: Active UK Government Security Check (SC). GenAI: Expertise in LLMs and RAG architectures. Python: Strong proficiency alongside PySpark for data engineering. Azure: Deep familiarity with native tools (AI Search, Document Intelligence). MLOps: Understanding of LLMOps frameworks ...

hands-on with Python and Azure , possessing a proven track record of designing and deploying Retrieval-Augmented Generation (RAG) patterns. Key Responsibilities Architect & Govern: Design and implement robust on-premises, cloud, and hybrid AI solutions, ensuring strict technical governance and best practices across … client relationships to secure consensus on complex technical architectures. Essential Skills Clearance: Active UK Government Security Check (SC). GenAI: Expertise in LLMs and RAG architectures. Python: Strong proficiency alongside PySpark for data engineering. Azure: Deep familiarity with native tools (AI Search, Document Intelligence). MLOps: Understanding of LLMOps frameworks ...

hands-on with Python and Azure , possessing a proven track record of designing and deploying Retrieval-Augmented Generation (RAG) patterns. Key Responsibilities Architect & Govern: Design and implement robust on-premises, cloud, and hybrid AI solutions, ensuring strict technical governance and best practices across … client relationships to secure consensus on complex technical architectures. Essential Skills Clearance: Active UK Government Security Check (SC). GenAI: Expertise in LLMs and RAG architectures. Python: Strong proficiency alongside PySpark for data engineering. Azure: Deep familiarity with native tools (AI Search, Document Intelligence). MLOps: Understanding of LLMOps frameworks ...

deploy Generative AI systems end to end – from use-case discovery through to production Build Retrieval-Augmented Generation (RAG) pipelines using vector databases, embeddings, and enterprise data sources Develop agent-based workflows, orchestration layers, and multi-step reasoning systems Work extensively with open-source … experience building and deploying Generative AI or applied ML systems Strong hands-on engineering background – you actively code, build, test, and deploy Experience with: RAG architectures and vector databases Hugging Face models, pipelines, and inference tooling Prompt engineering and LLM evaluation techniques Agentic systems and orchestration patterns Cloud-native experience ...

managing multi-API workflows using tools like LiteLLM to ensure flexibility and resilience. Building sophisticated Retrieval-Augmented Generation (RAG) systems, leveraging advanced techniques like embeddings with Voyage AI, rerankers , and query enrichment . Designing and maintaining efficient data pipelines and vector storage solutions using … PyTorch. Proven experience building and deploying applications with LLM APIs such as OpenAI , Anthropic , Gemini , and DeepSeek . Hands-on experience with the full RAG pipeline, including vector embeddings , rerankers , and data indexing in databases like MongoDB. Practical knowledge of LLM fine-tuning, prompt engineering, and performance optimization. Familiarity with ...

generative AI solutions for scientific and knowledge-discovery applications. Develop LLM-powered workflows and retrieval-augmented generation (RAG) systems for search, summarization, question answering, and evidence-grounded insight generation. Build intelligent retrieval, ranking, recommendation, and decision-support capabilities using modern orchestration frameworks … skills and solid machine learning fundamentals. Experience working with large-scale text or content-rich datasets and modern AI/ML frameworks. Experience with RAG, semantic, vector, or hybrid search, along with experimentation and evaluation approaches that measure user impact. Familiarity with cloud platforms and modern software engineering practices. Strong ...

tooling Copilot Studio Power Platform Enterprise Data Platforms Semantic Kernel LangChain Microsoft Agent Framework Retrieval-Augmented Generation (RAG) LLM-powered applications and intelligent agents MLOps, LLMOps and Cloud Native Architectures What we're Looking For You're likely already operating as an AI Architect … across both Generative AI and traditional Machine Learning Experience taking AI products from concept to production and ongoing operation Deep understanding of LLM architectures, RAG patterns and agent-based solutions Strong Azure and Microsoft ecosystem knowledge Experience designing secure, scalable and governed AI platforms Consulting experience with the ability ...

intelligent, distributed systems Architecting and building AI-driven capabilities , including: Large Language Models (LLMs) Retrieval-Augmented Generation (RAG) AI agents and orchestration workflows Designing and maintaining backend services and APIs (primarily Python, FastAPI/Flask) Building and scaling data pipelines and search systems using … Python or similar languages Significant experience with backend development , microservices, and distributed systems Hands-on experience with AI/ML systems , including LLMs, RAG, or vector databases Solid understanding of containerisation and orchestration (Docker/Kubernetes) Experience delivering secure, on-premise or regulated systems Proven ability to lead technically , mentor ...

integrating LLM-powered applications and workflows Evaluating model performance and mitigating failure modes Developing Retrieval-Augmented Generation (RAG) solutions Testing, troubleshooting and improving AI systems Contributing to technical standards and best practices Supporting the delivery of cutting-edge defence and AI programmes What … understanding of Machine Learning fundamentals and statistical methods Experience working with LLMs and Transformer architectures Knowledge of LLM evaluation and optimisation techniques Experience with RAG frameworks and modern AI tooling Strong problem-solving skills and engineering mindset Desirable: Defence or National Security experience AI Safety, Explainable AI or AI Security ...

Responsibilities Design & Deliver: Architect and implement cloud and AI-ready solutions on Azure, building repeatable patterns and integration services that support next-generation workloads. Secure AI Architecture: Develop and scale secure infrastructure architectures that allow applications to safely access both cloud-based backend services and on-premises data … Beyond the Basics): Real-world enterprise experience designing and deploying solutions centred around agentic workflows, Retrieval-Augmented Generation (RAG), and vectorisation patterns, rather than purely self-taught or personal interest projects. Software Engineering & Tech Stack: High proficiency in Python and PowerShell for building automation ...

security customers. Integrating AI components into existing applications, products, and operational workflows. Designing and implementing Retrieval-Augmented Generation (RAG) architectures. Evaluating Large Language Models (LLMs), identifying failure modes, and implementing mitigation strategies. Testing, validating, and debugging non-deterministic AI systems. Advising stakeholders … capabilities into production applications and business workflows. Strong understanding of LLM architectures, machine learning models, and statistical methods. Practical experience building and deploying RAG solutions. Experience evaluating AI systems and improving reliability, safety, and performance. Strong software engineering, architecture, and systems design fundamentals. Experience working in complex, high-stakes ...

implementing AI agents, automation workflows and AI-powered business solutions. Strong understanding of prompt engineering, Retrieval-Augmented Generation (RAG), tool/function calling and LLM integrations. Excellent business analysis, stakeholder management and workshop facilitation skills. Ability to translate complex business requirements into practical, scalable ...

implementing AI agents, automation workflows and AI-powered business solutions. Strong understanding of prompt engineering, Retrieval-Augmented Generation (RAG), tool/function calling and LLM integrations. Excellent business analysis, stakeholder management and workshop facilitation skills. Ability to translate complex business requirements into practical, scalable ...

operational problems. What You'll Be Working On Large Language Models (LLMs) Agentic AI systems Retrieval-Augmented Generation (RAG) AI-enabled decision support tools Secure and air-gapped AI deployments Production-grade AI applications used in mission-critical environments You'll work alongside experienced … accurate, robust and trusted. We're Looking For Engineers With Experience In Python development LLMs, Generative AI or Machine Learning AI evaluation and optimisation RAG frameworks and modern AI tooling Building and deploying production applications Solving complex technical problems Experience within Defence, National Security, Government or highly regulated environments ...

architectures on AWS, accelerating delivery of conversational AI products using Amazon Bedrock, agentic frameworks, and retrieval-augmented generation (RAG) patterns. Key responsibilities: Own the target-state architecture for GenAI products (voice and chat), including multi-account strategy, landing zone alignment, network patterns, and environment … segregation (dev/test/prod). Define reference architectures for Amazon Bedrock, model orchestration, RAG, tool/function calling, and agentic workflows (e.g., LangChain/LangGraph/CrewAI/Strands-style patterns) with clear guardrails. Design enterprise-grade knowledge architectures: ingestion pipelines, chunking strategies, embedding/model choices, vector ...