226 to 250 of 304 Retrieval-Augmented Generation Jobs in the UK

Data Factory, Azure Data Lake Storage, Azure SQL, Azure Functions, Azure Key Vault, Azure AI Search and Azure OpenAI where required. Support AI and RAG use cases by preparing structured and semi-structured data for retrieval, grounding, metadata enrichment and agent workflows. Implement data quality checks, validation rules … Microsoft DP-203 and/or DP-700 certification, or equivalent practical experience. Experience with Azure AI Search, Azure OpenAI, Azure AI Foundry or RAG-style data preparation. Experience integrating Microsoft 365, SharePoint, Teams, Dynamics, Salesforce, E-commerce or finance systems. Knowledge of OneLake shortcuts, Delta Lake, medallion architecture ...

include AI sales assistants, underwriting automation, internal summarisation systems, and workflow efficiency tools. Key Responsibilities • Build and deploy production-grade AI applications • Develop LLM, RAG, and agentic AI systems • Deploy applications into GCP environments • Work closely with cross-functional business stakeholders • Improve scalability, reliability, and AI deployment workflows • Build APIs … days per week in London office • Contract: 12-month FTC (maternity cover) • Tech stack: Python, GCP, APIs, Docker, Kubernetes, CI/CD, LLMs, RAG, LangChain/LlamaIndex • Sponsorship: Cannot sponsor Interested? Please apply below. ...

platform and infrastructure engineering role - not a data science or ML engineering position. You'll own the runtime, infrastructure, and operational layers that RAG pipelines, LLM orchestration, vector search, and evaluation workflows run on, across AWS and Databricks. The focus is on building scalable, observable, secure, and cost-efficient platform … infrastructure (OpenSearch, Algolia, AWS Bedrock Knowledge Bases) and embedding pipelines Build and maintain CI/CD pipelines for inference services, retrievers, ingestion workflows, and RAG components Implement observability across AI workloads using CloudWatch, MLflow, and OpenTelemetry - covering latency, throughput, cost, and system health Apply secure-by-design principles including ...

this is the clearest indicator of someone who has shipped LLM systems in production. • Deep, current LLM engineering practice. System-level prompt design, RAG, structured generation, fine-tuning trade-offs (SFT, DPO, LoRA), and working knowledge of the frontier model landscape. • LLM safety and security. Prompt injection mitigation ...

Contract AI Engineer | Outside IR35 | Agentic AI/LLMs/RAG Conquer AI is hiring a Contract AI Engineer We’re looking for a highly capable, hands-on AI Engineer with a strong traditional software engineering background and deep applied AI experience. This is an Outside IR35 contract working … greenfield AI projects for enterprise clients. You’ll be helping design and build real-world systems using LLMs, RAG, vector databases, agentic AI, and workflow automation. This is not a research-only role. We need someone who can build production-grade systems, integrate with existing platforms, and move quickly from ...

Applied AI Software Engineer - LangChain, LangGraph, RAG, Knowledge Graphs A high-growth, technology-led scale-up (backed by a global leading organisation) is expanding its engineering capability following a highly successful 2025. As part of significant continued investment, they are hiring a Software Engineer to lead the design and development … next-generation AI products and services across Finance, supporting both internal operations and external platforms. This is an opportunity to work in a modern, cloud-native engineering environment, building intelligent agentic AI systems that can reason, plan and act autonomously. You will take ownership of solutions ...

London. Known for their entrepreneurial culture and deep expertise across financial services, this is an exceptional opportunity to architect and deliver next-generation AI systems at the heart of some of the world's most complex financial institutions. You'll take a hands-on leadership role designing … that bring together multi-modal LLMs. Building agentic workflows that connect AI agents to live data sources and APIs, drawing on prompt engineering and RAG to drive accuracy and relevance Optimising and shipping large language and multi-modal models into production, balancing performance, latency, and reliability at enterprise scale Developing ...

OpenAI, Azure ML and Copilot Studio. Develop and manage CI/CD, LLMOps, and MLOps pipelines for Generative AI applications. Design and deploy GenAI, RAG and intelligent agent solutions across enterprise systems. Implement Infrastructure as Code (Terraform) and secure cloud environments following best practices. Support AI experimentation, model fine-tuning … across all AI initiatives. Required Experience Strong experience with Azure AI services, Azure OpenAI and AI infrastructure engineering. Hands-on expertise with Generative AI, RAG architectures, NLP and agentic workflows. Experience building secure CI/CD, LLMOps, and MLOps pipelines. Knowledge of Terraform, cloud security, APIs, and enterprise integrations. Familiarity ...

across products and enterprise transformation initiatives. What You'll Do Design and deploy AI agents and agentic workflows powered by LLMs Build systems using RAG, reasoning, planning, memory, and tool orchestration Develop multi-step AI solutions capable of autonomous decision-making and tool usage Work with MCP-style architectures … applications into production Hands-on expertise with LangChain, LangGraph, or similar frameworks Demonstrable experience building Agentic AI systems and AI agents Strong understanding of RAG architectures and LLM optimisation Experience with FastAPI, MCP/FastMCP, or similar technologies Familiarity with cloud-native AI deployments and data-driven applications Important Applications ...

PrivateLink for cross-cloud data connectivity. AI Readiness : Practical experience architecting data infrastructure for AI/ML consumption - vector databases, embedding stores, and RAG pipeline integration. Soft Skills: Strong interpersonal skills; ability to translate complex data architecture into clear language for Business Analysts and non-technical stakeholders. Duties Data Modelling … warehouse scheduling strategies to reduce operational data spend. AI Readiness: Architect data stores purpose-built for LLM consumption - including vector databases, embedding pipelines, and RAG-compatible data structures that will serve as the foundation for Bestway's AI product layer. Data Contracts : Partner with Business Analysts to formally define ...

multi-modal LLMs (text, image, audio, video), design agentic workflows enabling AI agents to interact with data sources and APIs using prompt engineering and RAG, optimise and deploy large language and multi-modal models with a focus on performance and latency and build scalable MLOps pipelines and full-stack applications … Langsmith, MCP (Model Context Protocol), bias mitigation techniques Apply now to find out more about this Backend Software Engineer/Developer (Python LLM MLOps RAG MCP) opportunity. ...

for. What you'll be working on as an AI Engineer - LLM & Agentic Systems: Designing and building AI agents and agentic workflows - combining LLMs, RAG, reasoning, memory and tool orchestration to solve real, complex business problems. Owning delivery end-to-end - from initial exploration through to production deployment, integration … with clear, real-world examples you can speak to confidently. Hands-on experience building AI agents including tool use, orchestration and multi-step reasoning - RAG systems that actually deliver, not just proofs of concept. Strong Python skills and solid machine learning foundations - able to write clean, production-grade code with ...

ideas to both technical and non‐technical audiences Nice to Have Research experience in areas such as large language models (e.g., training, fine‐tuning, RAG, evaluation, synthetic data generation), agentic AI, big data technologies, or digital twins Familiarity with emerging research and tooling ecosystems such as LangChain, LangGraph ...

based workflows, integrating AI platforms, and delivering scalable cloud-native solutions. Responsibilities AI Agent Engineering Design and implement AI agents, including: Retrieval (RAG) Orchestration workflows Tool/function invocation Policy-based routing Build evaluation frameworks for accuracy, latency, and reliability Implement observability and monitoring for agent lifecycle … engineering experience Strong experience with cloud-native systems (APIs, microservices, containers, serverless) Experience building and deploying AI/LLM-based systems in production (agents, RAG, orchestration) Proficiency in Python, Java, or similar backend languages Experience with: CI/CD pipelines Infrastructure as code Monitoring and observability tools Hands-on experience ...

Technical Project Manager - London/Hybrid - Fluent French - AI Delivery/RAG/Multi-Agent Systems - £40,000 - £60,000 The Role An ambitious and fast-growing AI consultancy are looking for a Project Manager with strong experience in AI to lead client engagements from discovery through to delivery. Working … concepts into practical business solutions. As a Project Manager here, you'll have the opportunity to work on cutting-edge AI initiatives involving RAG, multi-agent systems, modern LLM frameworks, and production AI deployments. You'll play a major role in shaping how projects are delivered and influence both technical ...

robust, production-ready solutions Designing and implementing machine learning models for complex applied problems Building and integrating modern AI systems using techniques such as RAG, LLMs, embeddings, vector search and multi-agent architectures Writing clean, performant Python code for production environments Working closely with engineering teams to improve architecture, reliability … delivery A pragmatic mindset and comfort working in a fast-paced scale-up environment It would be helpful if you also have experience with : RAG, LLMs, embeddings, vector databases or agent-based systems MLOps tools such as MLflow, Kubeflow or similar Docker, Kubernetes or containerised deployment environments Simulation, optimisation, decision ...

used across the business. AI Software Engineer - Responsibilities Design and deliver practical AI solutions Build and maintain LLM-powered applications, including retrieval-augmented workflows and tools integrations Collaborate with product and engineering teams to embed AI capabilities into software suite Establish best practice and champion … Engineer Experience - delivering production-ready solutions using Python, TypeScript or C# Hands on experience building LLM-based applications and solid understanding of retrieval-augmented generation approaches Experience leading projects or parts of projects from design through delivery Product mindset and collaborative approach - able ...

processing) AWS Bedrock, SageMaker, or similar managed AI services Observability frameworks for LLM systems (Langfuse, Arize, LangSmith) RAG pipelines, vector databases, or retrieval-augmented systems CI/CD automation; infrastructure-as-code (Terraform, CloudFormation) Why This Matters You're not building features. You're building ...

Engineer/Data Scientist – Agentic AI – £100k + Hybrid – HealthTech/Clinical Workflows Python | LLMs | RAG | AI Agents | OpenAI | Copilot | Elasticsearch | Vector DBs | Java | JavaScript | SaaS | Hybrid | Do you want to build AI features embedded directly into real clinical workflows used by hospitals, within a business actively rolling out GenAI … value to clinical users. Joining their engineering team, you’ll play a key role in designing and building Agentic AI systems, leveraging LLMs and RAG architectures to create production-ready capabilities that integrate seamlessly into the product. • You’ll develop AI-driven workflows including automated summaries, letter generation ...

deploying production AI applications using LLMs Designing agentic workflows and multi-step AI pipelines Developing scalable backend APIs and cloud-native services Creating RAG pipelines, embeddings and AI retrieval systems Improving AI reliability through testing, evaluation and guardrails Working closely with engineering, product and business teams Contributing … architecture decisions and AI best practice Helping shape the future direction of AI capability across the business Tech environment Python, AWS, APIs, LLMs, RAG, Docker, Kubernetes, microservices, cloud-native architecture and modern AI engineering tooling. What they're looking for Strong Python backend engineering experience Experience building and deploying ...

into practical AI solutions. Responsibilities Building, prototyping and deploying AI/LLM products Working with enterprise customers and internal engineering teams Using Python, LLMs, RAG, embeddings and vector databases Working with tools such as LangChain, LlamaIndex, OpenAI, Azure OpenAI or Anthropic Translating ambiguous business problems into working technical solutions Qualifications … Strong Python engineering experience Production experience with AI/LLM systems Hands-on RAG, prompt engineering, embeddings or vector database experience Confidence working with technical and non-technical stakeholders Comfortable in a client-facing, delivery-focused role Required Skills Strong Python engineering experience Production experience with AI/LLM systems ...

data with advanced machine learning and synthetic intelligence. The Role Design, build, and deploy Generative AI and LLM-based solutions for synthetic data generation and data augmentation Develop and validate statistical and machine learning methodologies to ensure data quality, reliability, and trust Work closely with Product and Engineering … datasets and collaborating with engineering teams Confidence explaining methodology, limitations, and impact to a broad range of stakeholders Exposure to synthetic data, prompt engineering, RAG, or cloud-based data platforms is beneficial but not essential ...

Meet Eloquent AI (YC X25) At Eloquent AI, we’re building the next generation of AI Operators—multimodal, autonomous systems that execute complex workflows across fragmented tools with human-level precision. Our technology goes far beyond chat: it sees, reads, clicks, types, and makes decisions—transforming how work … services that support real-time AI interactions, knowledge retrieval, and automation. Work closely with AI researchers and ML engineers to integrate LLMs, RAG, and automation into production-ready systems. Establish engineering best practices across testing, deployment, and performance optimisation. Continuously iterate and refine AI-driven products, balancing speed ...

work with clients, and help deliver production-grade AI systems. Our work is focused on real workflow automation. Think document intelligence, multi-step agents, RAG systems, data extraction, approval workflows, operational copilots, and AI systems that connect into the tools clients already use. This role sits close to what … client-facing problem solver. What you’ll be doing: Building agentic AI systems for complex enterprise workflows Working across Python, Node.js, TypeScript, APIs, LLMs, RAG, and data pipelines Helping design architecture for AI systems that need to be reliable, secure, and usable Joining client whiteboarding sessions to understand workflows ...

cloud-native AI stack is strongly desired (but not essential). Key Responsibilities/Experience • Design, prototype and deliver AI/ML PoCs (RAG pipelines, LLM-powered services, agent-based automation, generative use cases) aligned to Defence workflows and mission needs. • Build high-performance backend components to support AI workloads … JIRA-managed workflow tracking and stakeholder playback sessions. Essential Skills • Strong backend engineering background delivering high-scale systems with AI components (Python/Java, RAG frameworks, vector databases, API engineering). • Demonstrable experience fine-tuning and optimising LLM/ML models and associated training/inference pipelines. • Solid understanding ...