801 to 825 of 859 Retrieval-Augmented Generation Jobs in the UK

ship customer-facing applications, APIs and internal platforms. Remain hands-on with coding, testing, architecture and code reviews. Build AI-enabled products using LLMs, RAG, agents and model APIs. Take AI ideas from rapid prototypes through to reliable production systems. Work across Python, React/TypeScript, Django, FastAPI, PostgreSQL … scalability, security, reliability and maintainability. Technology Python | React | TypeScript | Django | FastAPI | PostgreSQL | AWS | Docker | REST APIs | CI/CD | Git AI experience across LLMs, RAG, agentic workflows, embeddings, prompt design or model evaluation is particularly valuable. What Theyre Looking For 510 years' commercial software engineering experience. Strong, recent hands-onPython ...

powered features within a modern C#/.NET application stack. Integrate Large Language Models (LLMs) and Generative AI into customer-facing products. Build RAG pipelines using vector databases and semantic search. Develop APIs and backend services that support AI functionality at scale. Work closely with Product, Engineering and Data teams … looking for Strong commercial experience developing backend applications in C# and .NET. Experience integrating AI or LLM technologies into production software. Understanding of RAG, embeddings, prompt engineering and vector search. Experience building scalable cloud-based applications using Azure. A genuine interest in Applied AI and solving real-world product problems. ...

powered features within a modern C#/.NET application stack. Integrate Large Language Models (LLMs) and Generative AI into customer-facing products. Build RAG pipelines using vector databases and semantic search. Develop APIs and backend services that support AI functionality at scale. Work closely with Product, Engineering and Data teams … looking for Strong commercial experience developing backend applications in C# and .NET. Experience integrating AI or LLM technologies into production software. Understanding of RAG, embeddings, prompt engineering and vector search. Experience building scalable cloud-based applications using Azure. A genuine interest in Applied AI and solving real-world product problems. ...

leadership across a multidisciplinary AI engineering team Shape the architecture and technical direction for AI across the product suite Lead the delivery of LLM, RAG and agentic AI solutions Take ideas from discovery and proof of concept through to production Establish standards for evaluation, security, observability, governance and cost control … ability to lead others, make architectural decisions and communicate technical trade-offs clearly to non-technical stakeholders. Experience with Azure OpenAI, Azure AI Search, RAG, agentic workflows, Semantic Kernel or Microsoft Agent Framework, vector databases, evaluation frameworks and responsible AI controls would be particularly useful. Salary and benefits ...

reusable platform services and enabling technologies across Azure (e.g. APIM, Azure AI Foundry, Databricks, MCP) that accelerate delivery of AI solutions such as Agents, RAG, and LLM-powered applications. You will work closely with architecture, AI engineering, and product teams to translate business needs into robust, platform‐first solutions, ensuring … codified engineering practices. What You Will Do Design and build scalable platform capabilities across Azure to support AI use cases (Agents, Agentic workflows, RAG, LLMs), including APIs, integrations, and model serving layers. Produce high‐quality technical designs and guide implementation, ensuring solutions are secure, maintainable, and aligned to architectural standards. ...

About Nexus Black IFS Nexus Black builds AI to solve hard problems for the industries that keep the world turning: up on power lines, down on factory floors, and out in the field. Our products ...

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 … long‐term quality and governance model for federated MCP contributions across LSEG.Skills\* Strong Python experience for test harnesses and automation.\* Experience with LLM and RAG evaluation frameworks or custom evaluation pipelines.\* Test automation expertise covering unit, integration, and regression testing.\* Understanding of agentic system risks and failure modes.\* Ability ...

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 … Ability to translate complex AI/ML designs into clear documentation. \* Knowledge of enterprise architecture principles (security, cloud, data, resilience). \* Familiarity with LLM, RAG, and agentic system architectures and risks. \* Strong stakeholder management and communication skills across technical and non-technical audiences.**Career Stage:**Manager**London Stock Exchange Group ...

About Brain Co. Brain Co. is an Applied AI startup founded by Elad Gil and Jared Kushner, and backed by many of Silicon Valley’s leading builders — including Patrick Collison (CEO of Stripe), Andrej Karpathy ...

Durable Functions, Temporal, Camunda or similar), decision tables (DMN), message backbones and CQRS-style read models. Practical, current knowledge of AI: LLMs, retrieval-augmented generation, agent patterns, and what it takes to run them safely over commercial customer data. Knowledge of the wider Microsoft ...

knowledge management, innovation, or legal technology environment.* Hands-on experience creating AI agents and working with modern large language models, including prompting, retrieval-augmented generation concepts, evaluation, workflow orchestration, and practical application to legal work.* Ability to collaborate effectively with AI Enablement, Data Modernization ...

attention to detail. Ability to work effectively within Agile squads and cross-functional environments. Desirable: Exposure to AI testing methods (e.g., validating LLM outputs, RAG consistency, AI behaviour evaluation). Experience using AI-powered QA tools or test-generation frameworks. Knowledge of cloud environments (AWS/Azure ...

tone alignment with The Economist's editorial voice; Design, curate, and manage fine-tuning datasets, including versioning and annotation workflows; Build and evaluate RAG pipelines incorporating retrieval from structured content; Prototype and test text-to-speech pipelines for audio-first products; Collaborate with infrastructure, frontend, and design leads … quality evaluation pipelines, including BLEU, ROUGE, editorial scoring, custom evaluations, and human-in-the-loop feedback loops; Support product experiments involving real-time generation, summarisation, or personalisation; Partner with journalists and editors to develop evaluation metrics capturing The Economist's tone and style. Требования 3+ Years of experience ...

platform. You will own ML components end to end — from research and prototyping through to production deployment — working across knowledge bases, vector stores, RAG pipelines, and context engines to power agents that deliver real impact for enterprise customers. You will: Own large areas of platform end to end, driving components … through to production deployment. Work on knowledge representation systems, including ontologies and knowledge graphs, to support structured reasoning over enterprise data. Design and implement RAG pipelines, including chunking, embedding, indexing, retrieval, and reranking. Build and maintain integrations between retrieval and ML components and diverse enterprise data ...

Join us as we build the next generation of AI and autonomous agents to solve critical operational challenges at the scale of the world's largest bank. You will have the opportunity to shape product strategy and delivery, working with cutting-edge technologies and collaborating with leaders across … launch. Familiarity with AI model architectures, including Large Language Models, and methods such as prompting, context engineering, fine-tuning, retrieval augmented generation, model context protocols, and agentic frameworks. Excellent stakeholder management, structured thinking, and ability to connect product work to business outcomes. Preferred Qualifications ...

hackajob is partnering directly with Google to hire for this role. Google's software engineers develop the next-generation technologies that change how billions of users connect, explore, and interact with information and one another. Our products need to handle information at massive scale, and extend well beyond … continue to push technology forward. AI in the Gemini Era is data-centric: the quality of the data used for training, fine-tuning, or RAG, matters more to the performance of the end product than almost anything else. Our mission is to improve the quality of models that Google releases ...

practical AI architectures and technical solutions Owning solution design from initial requirements through to delivery Architecting agentic AI systems using model APIs, orchestration frameworks, RAG and retrieval patterns Making informed decisions between different models, platforms, low-code solutions and custom development Designing integrations, APIs, data pipelines … Engineering or technical consulting backgrounds. You'll ideally bring strong experience across several of the following: AI/LLM solution architecture Agentic AI systems RAG and retrieval architectures Model APIs and orchestration frameworks Microsoft Copilot Studio Power Platform/Power Automate/Dataverse Azure and Microsoft 365 Python ...

rigor, and building an inclusive, collaborative culture. Deliver advanced AI and knowledge-discovery systems across the full lifecycle, from experimentation through production, including LLMs, RAG, search, and domain-enriched AI solutions. Drive evaluation and AI quality by establishing robust frameworks, metrics, experimentation practices, and responsible AI standards. Influence across product … data science methods, including machine learning, experimentation, deep learning, generative AI, and production AI systems. Hands-on experience delivering AI-powered products, including LLMs, RAG, semantic search, embeddings, agentic workflows, and knowledge-driven systems. Proven success leading and developing technical teams in complex product, platform, or research environments. Experience working ...

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. Internal Business Engagement: Build trusted relationships with senior stakeholders, translate complex concepts, and facilitate technical discovery workshops. … 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 concepts and standards. Software Engineering & API Design: Strong development background (ideally Java/JavaScript) coupled with robust API design ...

Foundry, Agent Framework and Microsoft IQ. Designing and implementing multi-agent workflows, including human-in-the-loop patterns and agentic orchestration. Creating robust RAG solutions using vector databases, Foundry IQ and agentic retrieval techniques. Developing predictive machine learning models with Azure Machine Learning to support forecasting, operational performance … maintainability. Hands-on experience, or a strong interest, in Microsoft AI technologies such as AI Foundry, Agent Framework, Azure Machine Learning, vector search and RAG architectures. Knowledge of responsible AI practices, observability, evaluation frameworks and human-in-the-loop design patterns. The ability to work closely with both technical ...

strong technical depth with delivery leadership and stakeholder management. You’ll implement AI and agentic systems across enterprise clients, designing scalable architectures using LLMs, RAG pipelines, and agentic workflows, while working closely with engineering and product teams to ensure successful outcomes. The Candidate Key attributes of the suitable Lead … Strong background delivering production-grade solutions, ideally within consulting or product-led environments. Agentic AI & Modern AI Systems Experience – Hands-on exposure to LLMs, RAG pipelines, and agentic Delivery Leadership & Client Ownership – Comfortable leading teams while remaining technically involved and managing client relationships post-sale ...

products, architecture and future AI roadmap. What you'll do Build AI-powered features within existing C#/.NET products Develop LLM solutions using RAG, agentic workflows and Azure AI Take ideas from proof-of-concept through to production Help shape technical decisions and the wider AI strategy Improve … moved beyond experimenting with AI and can demonstrate something you've genuinely delivered into production. Experience with Azure OpenAI, Azure AI Search, RAG, Semantic Kernel, vector databases or Python-based AI tooling would be particularly valuable. What's in it for you? Up to £70,000 plus bonus Mostly remote ...

focus on AWS and AWS Bedrock, working across business, technology and engineering teams. What you'll be doing Design and deliver Agentic AI, GenAI, RAG and AI-powered assistant solutions. Architect autonomous and multi-agent systems using AWS Bedrock, Lambda, Step Functions and related services. Work with frameworks such …/Agentic AI. Proven experience delivering production-grade AI agents or multi-agent solutions. Strong AWS experience, ideally including Bedrock. Hands-on experience with RAG and agentic AI frameworks. Excellent stakeholder, consulting and communication skills. Insurance or financial services experience desirable. If you're an experienced architect looking to work ...

team of engineers. Key Responsibilities * Lead the development and deployment of AI-powered tools to improve efficiency and productivity * Design advanced solutions including automation, RAG, and LLM-based workflows * Collaborate with stakeholders to identify and deliver strategic AI initiatives that deliver measurable business value * Provide guidance on AI architecture, tooling … with AI engineering, or software engineering (e.g. Python, Java, JavaScript/TypeScript etc.) with libraries/frameworks such as PyTorch, TensorFlow etc.) * Experience with RAG and LLM-based solutions * Solid understanding of AI architectures and data pipelines * Knowledge of security, compliance, and governance principles from a development perspective * Proven mentoring ...

just AI that demos well. What You'll Be Doing Design, build, and deploy production-grade AI software Apply emerging AI architecture patterns - RAG, agentic workflows, evals, fine-tuning, LLM orchestration directly into the product Collaborate closely with product and engineering teams to ship technical solutions at pace Ensure … machine learning/data science, with proven experience deploying models or AI systems into production Deep understanding of AI/ML architectures and patterns: RAG, prompt engineering, fine-tuning, evals, LLM orchestration, or equivalent applied ML/data science methods Python and/or TypeScript Comfortable working in a fast ...