426 to 450 of 498 Retrieval-Augmented Generation Jobs in London

teams to understand business and technical challenges. Design and develop AI-powered prototypes, proof-of-concepts and product solutions . Apply Generative AI, LLMs, RAG and prompt engineering to real-world use cases. Evaluate and integrate AI platforms, tools, APIs and cloud technologies. Contribute across the full product engineering lifecycle … experience across AI, software development and product engineering . Strong proficiency in Python and JavaScript . Hands-on experience with Generative AI, LLMs and RAG architectures . Experience with prompt engineering and AI APIs/integrations. Experience building prototypes, proof-of-concepts or production-ready solutions. Strong understanding of modern ...

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 the clients AI product layer. Data Contracts : Partner with Business Analysts to formally define ...

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 the clients AI product layer. Data Contracts : Partner with Business Analysts to formally define ...

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 ...

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. DutiesData Modelling Standard … 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 ...

production LLM systems that deliver accurate, valuable outcomes for real users. You’ll be responsible for: Building and improving production LLM-driven systems , including RAG and agentic workflows. Developing high-quality, reliable and well-tested Python code. Designing and implementing evaluations (evals) that genuinely measure whether AI systems are improving. … ideally have: 4+ years' experience building production software. 2+ years' experience building production LLM applications. Strong hands-on experience with Python . Experience building RAG systems , LLM applications and/or AI agents. A strong understanding of how LLM systems work, including areas such as embeddings, prompting and model parameters ...

work includes:\* Building and operating LSEG AI Assist, an in‐house agentic experience capable of reasoning, planning, and tool‐calling.\* Operating QAS, the enterprise RAG and search layer used to ground agent responses in approved data sources.\* Delivering a production Internal MCP Gateway providing discovery, security, policy enforcement, observability … understanding of Model Context Protocol (MCP), including server and tool patterns.\* FastAPI and REST API design and implementation experience.\* Experience with prompt engineering and RAG‐based architectures.\* Containerisation and Kubernetes‐based deployment experience.\* Ability to work across platform, product, and governance boundaries in an enterprise environment.**Career Stage:**Manager**London ...

governance, design standards, and manage risk, non-functional requirements (NFRs), and technical debt. Agentic AI & Commerce Innovation: Design AWS-based agentic AI platforms (orchestration, RAG, memory, guardrails, and MCP). Establish reusable patterns and advise clients on emerging Agentic Commerce standards (ACP, AP2, A2A, and secure payment models).Client Engagement … including serverless patterns and appropriate integration components).Agentic AI & Commerce: Strong understanding of building agentic AI platforms on AWS (e.g., Bedrock, orchestrations, RAG, gateways/MCP) and awareness of emerging Agentic Commerce concepts and standards (ACP, AP2, A2A).Software Engineering & API Design: Strong development background (ideally TypeScript/JavaScript) coupled ...

GStreamer, NVIDIA NeMo). Connect video processing stages to computer-vision and multimodal AI models (for tasks like classification, embeddings, and structured output generation). Prototype and optimize codec-aware inference workflows to improve accuracy, latency, and cost. Requirements: Strong Python: Proven commercial experience writing clean, scalable … GStreamer. Familiarity with GPU-accelerated video/AI tech (CUDA, PyTorch, TensorRT, DeepStream). Experience with multimodal AI (VLMs, LLM APIs, Retrieval-Augmented Generation). Cloud and containerization skills (AWS, Docker). ...

Azure (azure Open AI service, Cosmos DB)PythonLangGraphNeo4j/cypherOther coding languages/frameworks e.g. Java/.NetAI RAG (retrieval augmented generation)Graph RAGFew shot detectionEmbedding models/LLMs - how they work, how they are trained Who we are: We're a business with ...

challenge design decisions, and assess technical risk Deep expertise in enterprise AI applications built on large language models, including agents, retrieval augmented generation, orchestration frameworks, model optimization, and evaluation frameworks Hands-on experience building AI/ML applications (RAG, agent frameworks, MCPs, skills, harnesses … delivery outcomes across the portfolio Drive architectural decisions, organizational alignment, and integration of AI-powered solutions using large language models, retrieval augmented generation, orchestration frameworks, and agentic workflows Establish engineering excellence through architecture reviews, code reviews, automated testing, observability, security standards, operational excellence ...

challenge design decisions, and assess technical risk Deep expertise in enterprise AI applications built on large language models, including agents, retrieval augmented generation, orchestration frameworks, model optimization, and evaluation frameworks Hands-on experience building AI/ML applications (RAG, agent frameworks, MCPs, skills, harnesses … delivery outcomes across the portfolio Drive architectural decisions, organizational alignment, and integration of AI-powered solutions using large language models, retrieval augmented generation, orchestration frameworks, and agentic workflows Establish engineering excellence through architecture reviews, code reviews, automated testing, observability, security standards, operational excellence ...

building and fine-tuning LLM-powered systems with a particular focus on editorial tone, style transfer, retrieval workflows, and multimodal generation (especially audio). You'll ship products from zero-to-one and see your ideas directly influence how millions of readers interact with our journalism. … tone alignment with our editorial voice Design, curate, and manage datasets used for fine-tuning, including versioning and annotation workflows Build and evaluate RAG pipelines that incorporate retrieval from structured content Prototype and test TTS (text-to-speech) pipelines for use in audio-first products (leveraging tools like ...

chosen and the result measured against clear success criteria. Leading the design of generative and agentic AI solutions, including prompting, retrieval augmented generation, tool use and multi-step agent workflows, and the techniques needed to make them accurate and reliable. Selecting the right approach … governance forums. What you need to haveStrong, hands-on expertise with large language models and generative AI, including prompt engineering, retrieval augmented generation, fine tuning, and the design and evaluation of agentic systems that use tools and operate over multiple steps. Strong programming ability ...

agentic technologies. Key responsibilities Own the technical POC from scope through to demonstration Build front-end and back-end components Design and implement RAG and retrieval capabilities Work with vector databases and/or knowledge graphs Develop agentic workflows and supporting harnesses Build evaluation frameworks and assess … iterate and demonstrate solutions Work closely with architects, data specialists and client technical teams Experience required Strong hands-on AI/LLM engineering experience RAG and retrieval architectures Agentic AI/workflows Strong software engineering capability across front and back end Azure and Azure OpenAI/OpenAI Experience ...

business problem and shaping the solution through to deployment, monitoring and continuous improvement. Your work could include building a retrieval‐augmented generation solution that helps customer service agents access the right information, developing an agentic workflow that automates campaign planning and optimisation, productionising recommendation … from problem definition through to live service and iteration. Develop generative AI solutions using prompt and context engineering, coding, retrieval‐augmented generation, fine‐tuning and applying evaluation techniques. Implement and optimise agentic AI workflows and multi‐step reasoning pipelines, integrating them with enterprise systems ...

testing and production readiness. Test APIs and integrations across internal and external services. Validate AI-generated outputs for accuracy, relevance, consistency and grounding. Assess RAG and retrieval performance, ensuring relevant information is retrieved and used appropriately. Establish repeatable evaluation approaches and datasets for AI-enabled functionality. Work with … tooling such as Jira or Azure DevOps. Good technical understanding of web applications, APIs and modern application architectures. Experience testing Generative AI, LLM or RAG solutions would be highly desirable. Understanding of AI evaluation concepts including groundedness, relevance, hallucination testing and retrieval quality. Strong analytical, problem-solving ...

Build AI workflows in Azure AI Foundry (project spaces, model registry, prompt flow, safe deployment) Develop and deploy LLMs via Azure OpenAI and implement RAG with Azure AI Search Create and integrate Copilot agents (Copilot Studio/M365 Copilot) and AIpowered apps/services Set up CI/CD, monitoring … generative AI/LLM experience on Azure Handson with Azure AI Foundry/Azure AI Studio and Azure OpenAI Strong Python, API integration, and RAG/vector search skills Familiarity with Copilot Studio or M365 Copilot is a strong plus. #J-18808-Ljbffr ...

Senior Software Engineer to join a growing AI team and take ownership of the application and integration layer behind a new generation of AI-powered products. This is a genuinely full-stack engineering role, combining production-grade backend development, API design, AI integrations and frontend engineering. … securely and reliably. Experience working closely with designers to deliver production-quality frontend applications. A good understanding of accessibility and frontend performance. Experience with RAG, AI agents, tool use or other generative AI application patterns would be advantageous, although deep ML expertise isn't required. This is an opportunity ...

Senior Software Engineer to join a growing AI team and take ownership of the application and integration layer behind a new generation of AI-powered products. This is a genuinely full-stack engineering role, combining production-grade backend development, API design, AI integrations and frontend engineering. … securely and reliably. Experience working closely with designers to deliver production-quality frontend applications. A good understanding of accessibility and frontend performance. Experience with RAG, AI agents, tool use or other generative AI application patterns would be advantageous, although deep ML expertise isn't required. This is an opportunity ...

capability while setting clear objectives and priorities.* Oversee the design, delivery, and ongoing support of high-quality AI solutions including generative AI models, RAG-based architectures, agentic systems, and machine learning applications.* Collaborate closely with Digital Transformation teams and business stakeholders to understand requirements, shape opportunity pipelines, translate demand into … within complex organisations—demonstrating empathy for your colleagues' development while maintaining high standards of accountability. Your expertise spans designing advanced generative AI systems leveraging RAG architectures/vector databases/model evaluation frameworks/LLMOps practices alongside deep familiarity with cloud platforms like Azure/AWS. You possess thorough knowledge ...

real client data during Assess engagements - the prototype is the discovery tool, built while the value case is made * Delivering client POCs and MVPs: RAG pipelines, agent architectures, LLM integrations and protocol-driven tooling (MCP, tool orchestration) * Iterating in short loops: demoing every few days, taking feedback, changing course without … front-end, back-end and data engineering to build the whole thing yourself * Hands-on production LLM and agent experience: prompt engineering, agent workflows, RAG, tool orchestration and MCP - with evidence you've shipped AI users actually rely on, and how you proved it could be trusted * Evaluation-driven habits ...

real client data during Assess engagements, the prototype is the discovery tool, built while the value case is made Delivering client POCs and MVPs: RAG pipelines, agent architectures, LLM integrations and protocol-driven tooling (MCP, tool orchestration) Iterating in short loops: demoing every few days, taking feedback, changing course without … front-end, back-end and data engineering to build the whole thing yourself Hands-on production LLM and agent experience: prompt engineering, agent workflows, RAG, tool orchestration and MCP, with evidence you've shipped AI users actually rely on, and how you proved it could be trusted Evaluation-driven habits ...

Cloudflare’s global network, from frontier open LLMs and real-time voice models to customer-deployed models served on heterogeneous GPUs and next-generation accelerators. You’ll work with systems engineers, product teams, hardware partners, and AI/ML engineers to bring models into production with low latency … such as SGLang, vLLM, TensorRT-LLM, ONNX Runtime, Triton, llama.cpp, or similar. Familiarity with LLMs, speech models, vision models, embeddings, multimodal models, retrieval-augmented generation, or other modern deep learning architectures. Experience optimizing models for GPUs or specialized accelerators. Strong understanding of production ...

inference workflows, guiding teams through design reviews and hands-on coding. You will work across AWS/Azure/GCP, apply retrieval-augmented generation, and champion responsible AI governance while mentoring engineers and delivering high-impact AI solutions at scale. #J-18808-Ljbffr ...