1 to 25 of 137 Permanent Retrieval-Augmented Generation Jobs in the UK

organization. The team designs, develops, and supports enterprise-grade AI applications, including Generative AI, Retrieval-Augmented Generation (RAG), and Agentic AI solutions. Hybrid working: The places that you work from day to day will vary according to your role, your needs, and those … success criteria for AI initiatives. Design, develop, and deliver scalable AI solutions, including Generative AI, Retrieval-Augmented Generation (RAG), Agentic AI, and intelligent automation capabilities aligned to business objectives. Evaluate technology, model, and platform options, providing recommendations based on business value, cost, risk, strategic ...

features and applications using LLMs, including intelligent document processing, information extraction and automated workflows. Develop retrieval-augmented generation (RAG) solutions that connect LLMs with internal data, documents and other knowledge sources. Build and integrate APIs to connect applications, databases, CRM platforms and third-party … LLMs: Practical experience integrating large language models into applications or developing AI-powered functionality. Retrieval-Augmented Generation (RAG): Experience building or implementing RAG pipelines that enable LLMs to retrieve and use relevant information from documents, databases or other knowledge sources. Application architecture: An understanding ...

develop and evaluate AI-powered proof-of-concepts that demonstrate how Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI assistants and agentic AI technologies can improve operational efficiency, automate investigative tasks and support security analysts. What You'll Be Doing Designing and building … security operations. Creating AI assistants, copilots and agent-based workflows to enhance analyst productivity. Implementing Retrieval-Augmented Generation (RAG) solutions using enterprise knowledge sources. Applying prompt engineering techniques to optimise AI performance and accuracy. Integrating AI capabilities with SIEM, SOAR and other cyber security ...

develop and evaluate AI-powered proof-of-concepts that demonstrate how Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI assistants and agentic AI technologies can improve operational efficiency, automate investigative tasks and support security analysts. What You'll Be Doing Designing and building … security operations. Creating AI assistants, copilots and agent-based workflows to enhance analyst productivity. Implementing Retrieval-Augmented Generation (RAG) solutions using enterprise knowledge sources. Applying prompt engineering techniques to optimise AI performance and accuracy. Integrating AI capabilities with SIEM, SOAR and other cyber security ...

enterprise standards. Design enterprise-scale AI architectures covering agent orchestration, large language models (LLMs), retrieval-augmented generation (RAG), knowledge management, integrations, governance, security, and observability. Assess client technology landscapes, data estates, cloud platforms, and security frameworks to establish the foundations required for successful … focused organizations. Technical Knowledge Strong understanding of Large Language Models (LLMs), Generative AI, Agentic AI, Retrieval-Augmented Generation (RAG), AI orchestration frameworks, and AI application architectures. Knowledge of cloud platforms including Microsoft Azure, AWS, and Google Cloud. Experience with modern data platforms including Databricks ...

conversational assistants, workflow automation and intelligent document processing Developing applications using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) and agent-based approaches Taking solutions from prototype through to deployment, monitoring and continuous improvement Building and maintaining APIs, integrations and data pipelines that support … Demonstrable ability to learn new technologies quickly Desirable Experience Agentic AI or AI agent frameworks Retrieval-Augmented Generation (RAG) Workflow automation platforms AI evaluation, monitoring or observability Experience working within regulated environments Agile delivery experience About YouThis organisation is placing particular emphasis on mindset ...

agentic AI. Continuous Learning: Stay updated with the latest trends in the AI engineering field, such as the modern AI stack, synthetic data generation, and Explainable AI. … Skills/Experience: Engineering Foundations: Strong proficiency in Python and robust software engineering principles, with experience operating as part of engineering teams. Generative AI & RAG: Proven experience working with LLMs and designing Retrieval-Augmented Generation (RAG) architectures, including knowledge of semantic search and vector ...

PyTorch FastAPI Knowledge Graphs Kubernetes Docker Infrastructure as Code MLOps Event-Driven Architecture Vector Databases Retrieval-Augmented Generation (RAG) Technology Stack Python SQL FastAPI PyTorch Docker Kubernetes AWS Azure Git CI/CD Knowledge Graphs AI/Large Language Models (LLMs) Amazon Bedrock Azure ...

standards across AI projects. Design and deliver solutions involving generative AI, large language models (LLMs), retrieval-augmented generation (RAG), prompt engineering and agentic AI. Establish robust approaches to model evaluation, monitoring, performance measurement and continuous improvement. Drive high-quality engineering practices, including Python development … machine learning solutions into production. Strong technical leadership and architecture experience across AI engineering and software delivery. Practical knowledge of generative AI, LLMs, RAG, prompt engineering, agentic AI and model evaluation. Strong Python development skills and a sound understanding of software engineering best practice. Experience delivering AI solutions at scale ...

Collaborate with multidisciplinary teams to develop Generative AI proof-of-concepts using technologies such as Retrieval-Augmented Generation (RAG) and intelligent agents. Scale successful proof-of-concepts into robust, production-ready solutions. Design and develop full stack applications across both AI-driven and traditional … success. You will work on impactful projects, contribute to the adoption of emerging technologies and play a key role in delivering next-generation AI solutions. Reasonable Adjustments: Respect and equality are core values to us. We are proud of the diverse and inclusive community we have built ...

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 ...

Agents & Automation Design, develop, and manage AI agents, copilots, and workflow automation solutions. Build Retrieval-Augmented Generation (RAG) applications leveraging internal business data. Develop intelligent assistants supporting operational, engineering, customer service, and business functions. Implement multi-agent workflows and orchestration frameworks. Monitor and optimise … enterprise environments. Strong Python development skills. Experience integrating and consuming REST APIs. Hands-on experience with Docker and Kubernetes. Knowledge of vector databases, embeddings, RAG architectures, and LLM orchestration frameworks. Experience with cloud technologies, networking, identity and access management, and security controls. Experience integrating AI solutions with Microsoft 365 technologies ...

public sector and commercial experience Successful academic background in your specialist discipline Familiarity with Retrieval-Augmented Generation (RAG), vector databases, embeddings, and other patterns used to support Generative AI solutions on platforms such as Amazon Bedrock. Experience developing data-based apps in Streamlit/ ...

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 ...

Platform Engineer LLMs RAG Python Cloud Infrastructure Manchester City Centre - 5 days a week onsite Up to £100,000 DOE The Opportunity We're looking for an AI Platform Engineer to build, optimise and maintain the infrastructure behind a growing portfolio of AI-powered applications. You'll focus on developing … scalable, reliable services supporting large language models (LLMs), retrieval-augmented generation (RAG), intelligent search and conversational AI. You'll take ownership of existing solutions while helping bring new AI capabilities into production. Key Responsibilities - Design, build and optimise production-grade AI platforms, RAG pipelines ...

Platform Engineer LLMs | RAG | Python | Cloud Infrastructure Manchester City Centre - 5 days a week onsite Up to £100,000 DOE The Opportunity We're looking for an AI Platform Engineer to build, optimise and maintain the infrastructure behind a growing portfolio of AI-powered applications. You'll focus on developing … scalable, reliable services supporting large language models (LLMs), retrieval-augmented generation (RAG), intelligent search and conversational AI. You'll take ownership of existing solutions while helping bring new AI capabilities into production. Key Responsibilities - Design, build and optimise production-grade AI platforms, RAG pipelines ...

help onboard new team members. Work alongside senior engineers, including colleagues experienced in AI and retrieval-augmented generation (RAG), to build the teams confidence in applying AI to practical problems. Contribute to frontend and backend work according to your experience, developing a broader understanding … problems customers face and how users interact with our products. Explore relevant approaches with senior engineers, drawing on any experience of vector search, embeddings, RAG, fine-tuning, prompt engineering or AI orchestration frameworks such as LangChain. Help evaluate model output quality through structured examples and lightweight evaluation sets. Where relevant ...

Salesforce Einstein or Agentforce. Experience working with in-house or enterprise LLMs, including prompt design, retrieval-augmented generation (RAG) knowledge sources or evaluating AI output quality. Experience with workflow automation tools. Knowledge of the cybersecurity or data security industry. Applicants must be legally authorized ...

Azure AI services. * Build multi-agent systems and AI-powered workflows, integrating with existing applications and data sources. * Apply techniques such as prompt engineering, RAG and agent orchestration to improve AI performance. * Implement AI security, monitoring, testing and governance measures. * Take ownership of solutions throughout the full development lifecycle, from … integration. * Experience with Azure AI services, Azure OpenAI, AI Search or similar technologies. * Understanding of Retrieval-Augmented Generation (RAG), prompt engineering and AI orchestration. * Python experience is desirable but not essential. * Experience working with Public Sector, or other regulated environments would be beneficial. * Must ...

agent-based patterns, workflow orchestration and enterprise AI integration. Practical experience applying techniques such as retrieval-augmented generation (RAG), knowledge grounding, prompt engineering and human-in-the-loop design patterns. Experience designing secure and controlled AI solutions, including guardrails, responsible AI, explainability and governance ...

industry is a plus. Strong foundational understanding of modern AI and agentic application patterns, including retrieval-augmented generation (RAG), semantic search, and agent-based system design. Hands-on experience building backend services, APIs, and production systems. Experience working across architecture, data, and platform concerns ...

shipping AI-powered products end-to-end using LLM technologies. Owning and scaling the retrieval-augmented generation (RAG) and AI application layer. Developing secure, production-grade systems including guardrails, evaluation frameworks, monitoring, caching, and token cost optimisation. Working across the stack, including backend services ...

. Experience building pipelines for structured and unstructured data using both vector databases and retrieval-augmented generation (RAG)-like architectures to power enterprise AI solutions. Experience leading technical discovery sessions. Preferred qualifications: Masters degree or PhD in Artificial Intelligence, Computer Science, or a related ...

Data, AI & Intelligent Systems Expertise: Experience or strong interest in one or more of the following: Generative AI, LLMs, Retrieval Augmented Generation (RAG) and AI applications Agentic AI, AI agents, intelligent assistants and AI-enabled automation Prompt engineering, AI evaluation and Responsible ...