101 to 125 of 175 Retrieval-Augmented Generation Jobs in London

serve humanity. We're training and deploying frontier models for developers and enterprises who are building AI systems to power magical experiences like content generation, semantic search, RAG, and agents. We believe that our work is instrumental to the widespread adoption of AI. We obsess over what we build. Each one of us is responsible for contributing to More ❯

Engineers to help build two new football-focused chatbots for betting audiences. Youll be responsible for designing, building, and deploying AI-powered conversational agents using LangGraph, OpenAI functions, and RAG techniques. This is a hands-on engineering role where you get to ship real-time chatbots that deliver dynamic, contextual betting insights to end users. Responsibilities: Build conversational AI flows … using LangGraph and OpenAI function-calling Integrate live sports data, betting odds, and user context into dynamic responses Implement memory handling, tool usage, and RAG pipelines Collaborate on system design, prompt tuning, and architecture decisions Optimize performance for speed, stability, and user satisfaction Skills & Experience: Proven experience with LangChain or LangGraph Strong Python skills and experience working with LLMs Familiarity … with RAG pipelines Experience building chatbots or agent-based systems Knowledge of real-time APIs and data integration (e.g., live sports feeds, betting odds) Understanding of prompt engineering, token limits, and response tuning Bonus: Experience in sports analytics, fantasy sports, or betting applications About us: At Peregrine, we see beyond the immediate and look to the horizon. We build lasting More ❯

to help build two new football-focused chatbots for betting audiences. You’ll be responsible for designing, building, and deploying AI-powered conversational agents using LangGraph, OpenAI functions, and RAG techniques. This is a hands-on engineering role where you get to ship real-time chatbots that deliver dynamic, contextual betting insights to end users. Responsibilities: Build conversational AI flows … using LangGraph and OpenAI function-calling Integrate live sports data, betting odds, and user context into dynamic responses Implement memory handling, tool usage, and RAG pipelines Collaborate on system design, prompt tuning, and architecture decisions Optimize performance for speed, stability, and user satisfaction Skills & Experience: Proven experience with LangChain or LangGraph Strong Python skills and experience working with LLMs Familiarity … with RAG pipelines Experience building chatbots or agent-based systems Knowledge of real-time APIs and data integration (e.g., live sports feeds, betting odds) Understanding of prompt engineering, token limits, and response tuning Bonus: Experience in sports analytics, fantasy sports, or betting applications About us: At Peregrine, we see beyond the immediate and look to the horizon. We build lasting More ❯

ll take the lead in shaping end-to-end Azure AI architectures, from discovery and PoCs through to delivery and optimisation. You'll work directly with enterprise clients, defining RAG systems, Agentic AI solutions, knowledge base integrations, and driving forward both client success and internal AI accelerators. Key Responsibilities: Design scalable, secure Azure AI architectures tailored to client needs. Work … closely with customer business and technical stakeholders. Define and deliver solutions involving RAG systems, Agentic AI, knowledge bases, and MCP integrations. Lead pre-sales engagements including PoCs, workshops, and stakeholder briefings. Collaborate with engineers, analysts, and scientists to guide delivery. Ensure best practice in responsible AI, data management, and security. Monitor performance and optimise ongoing AI solutions. Contribute to internal More ❯

Founding Engineer Location: Hybrid (2–3 days/week in London office) I am representing a fast-moving, mission-driven start up building an AI-powered clinical knowledge platform. What You’ll Do: Build and scale backend services (Python/ More ❯

Founding Engineer Location: Hybrid (2–3 days/week in London office) I am representing a fast-moving, mission-driven start up building an AI-powered clinical knowledge platform. What You’ll Do: Build and scale backend services (Python/ More ❯

Engineer The role is building AI based automation into back-office administration tasks. You'll be working with GenAI and Agentic AI, lots of AWS, NodeJS, Python, HuggingFace, LangChain, RAG techniques, interfacing with diverse data sets. The opportunity Work at the forefront of the industry. It's exciting, competitive, fast paced and challenging of course! You'll have the support More ❯

Engineer The role is building AI based automation into back-office administration tasks. You'll be working with GenAI and Agentic AI, lots of AWS, NodeJS, Python, HuggingFace, LangChain, RAG techniques, interfacing with diverse data sets. The opportunity Work at the forefront of the industry. It's exciting, competitive, fast paced and challenging of course! You'll have the support More ❯

Engineer The role is building AI based automation into back-office administration tasks. You'll be working with GenAI and Agentic AI, lots of AWS, NodeJS, Python, HuggingFace, LangChain, RAG techniques, interfacing with diverse data sets. The opportunity Work at the forefront of the industry. It's exciting, competitive, fast paced and challenging of course! You'll have the support More ❯

PMP and CSM certifications or equivalent project management certification Strong understanding of AI/ML technologies and cloud computing platforms PREFERRED QUALIFICATIONS Experience with GenAI technologies (LLMs, Foundation Models, RAG) Experience in technology consulting or professional services Executive presence and stakeholder management abilities Ability to translate complex AI concepts for business audiences More ❯

Vision/NLP Strong Software Engineering skills (3 years+) Developed LLM architecture and deployed LLM applications Uptodate with current trends in AI Some experience with applying latest techniques like RAG architecture, GenAI, Parallel training etc The role is hybrid, with adhoc requirements to be on client premises (London) this could be between 1-3 days a week, so we would More ❯

Vision/NLP Strong Software Engineering skills (3 years+) Developed LLM architecture and deployed LLM applications Uptodate with current trends in AI Some experience with applying latest techniques like RAG architecture, GenAI, Parallel training etc The role is hybrid, with adhoc requirements to be on client premises (London) this could be between 1-3 days a week, so we would More ❯

Java, SQL) is a plus. Passion for learning and sharing knowledge with others. Nice to Have Experience with GenAI, Agentic AI, or LLMs. Exposure to technologies like vector databases, RAG, or containerisation (Docker/Kubernetes). Relevant certifications and a professional degree. UK security clearance (BPSS or SC). Why Join? You'll be part of a collaborative, innovative team More ❯

For: Experience building SaaS platforms, especially in Fintech. Background in autonomous systems, workflow automation, or AI-driven decision engines. Experience with tools like LangChain, semantic search, vector databases, or RAG pipelines. Why Join? Be part of the founding team of a well-funded, high-potential startup. Work on problems that are messy, complex, and hugely valuable Competitive salary + early More ❯

intermediate or higher English proficiency Experience with usage of the LLM-based solutions in daily workflow (ChatGPT, CoPilot, JetBrains AI Assistant, etc). Understanding of vector databases, embeddings, and RAG implementations Strong problem-solving skills and a growth mindset Experience working in a growth team, implementing projects with open technical specifications, and the ability to solve problems "on the fly. More ❯

e.g. React/Angular and integration with backend - AWS experience or working knowledge of AWS partner solutions like Databricks or Snowflake - Expertise of implementing GenAI in production including LLMs, RAG architectures, vector databases. - Experience with automation and scripting (e.g., Terraform, Python). - Knowledge of security and compliance standards (e.g., HIPAA, GDPR). Amazon is an equal opportunities employer. We believe More ❯

doing Design and maintain pipelines that support LLM-based features - including metadata processing, semantic enrichment, and structured context retrieval. Design infrastructure for scalable and performant RAG systems (retrieval-augmented generation), including support for Graph RAG where adopted. Experience in processing large volumes and varieties of structured text data. Experience with legal documents would be … advanced features, not just move bytes around. You've worked with vector stores and embedding pipelines. You are excited by newer patterns like hybrid and graph-based retrieval (Graph RAG). You're comfortable owning your systems in production and instrumenting them for observability. You value collaboration and can flex across infrastructure, science, and product conversations. Qualifications 5+ … services; experience with Amazon Bedrock or Claude integration is a plus. Experience with vector databases and embedding pipelines. Familiarity with or interest in graph-based data models and Graph RAG architectures is a strong plus. Working knowledge of Java and TypeScript environments, especially for integration and debugging. Experience using Jira to coordinate delivery. Working for Opus 2 Opus 2 is More ❯

efficiency at scale. Key Responsibilities: AI System Development: Design and implement advanced AI solutions to automate and optimize business processes, ensuring high performance, scalability, and reliability. Agentic LLM/RAG Systems: Build sophisticated agentic systems leveraging Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), optimizing for performance and cost by selecting appropriate models More ❯

efficiency at scale. Key Responsibilities: AI System Development: Design and implement advanced AI solutions to automate and optimize business processes, ensuring high performance, scalability, and reliability. Agentic LLM/RAG Systems: Build sophisticated agentic systems leveraging Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), optimizing for performance and cost by selecting appropriate models More ❯

Doing Designing, training, and deploying computer vision models to recognize exhibits and physical objects across large venues Integrating LLMs and retrieval-augmented generation (RAG) systems to enable contextual, safe, and engaging visitor conversations Developing voice interfaces using speech-to-text and text-to-speech for seamless hands-free experiences Building scalable infrastructure, backend APIs More ❯

object detection (e.g. MobileNet, YOLO). Either way, we’re looking for someone who can help our app understand what the visitor is looking at – reliably and at scale. RAG Systems, Data Pipelines & Internal Agents: You'll design the data pipelines that power our AI features, including retrieval-augmented generation (RAG), internal LLM-based More ❯

object detection (e.g. MobileNet, YOLO). Either way, we’re looking for someone who can help our app understand what the visitor is looking at – reliably and at scale. RAG Systems, Data Pipelines & Internal Agents: You'll design the data pipelines that power our AI features, including retrieval-augmented generation (RAG), internal LLM-based More ❯

time using image embeddings, similarity search (e.g. CLIP, vector search), and traditional CV approaches (e.g. YOLO, MobileNet). 🔹 LLM & RAG Systems: Design and implement pipelines that support retrieval-augmented generation, internal AI tools, and scalable content delivery. Experience with vector databases, agent frameworks, or data workflows is highly relevant. 🔹 Deployment & MLOps: Own model deployment More ❯

time using image embeddings, similarity search (e.g. CLIP, vector search), and traditional CV approaches (e.g. YOLO, MobileNet). 🔹 LLM & RAG Systems: Design and implement pipelines that support retrieval-augmented generation, internal AI tools, and scalable content delivery. Experience with vector databases, agent frameworks, or data workflows is highly relevant. 🔹 Deployment & MLOps: Own model deployment More ❯

object detection (e.g. MobileNet, YOLO). Either way, we’re looking for someone who can help our app understand what the visitor is looking at – reliably and at scale. RAG Systems, Data Pipelines & Internal Agents: You'll design the data pipelines that power our AI features, including retrieval-augmented generation (RAG), internal LLM-based More ❯