376 to 400 of 498 Retrieval-Augmented Generation Jobs in London

have Experience building, deploying, and maintaining machine-learning pipelines in production (the maintenance matters as much as the building). Experience with Retrieval-Augmented Generation, and with vector or graph databases. Familiarity with a modern data stack: Databricks, dbt, DLT, Unity Catalog or similar. ...

production, and guide delivery with senior client teams. Based in London or other major UK hubs, you will lead hands-on engineering, contribute to RAG pipelines and eval frameworks, and mentor engineers while embedding GenAI and governance into client journeys. #J-18808-Ljbffr ...

pathway to the Forward Deployed Engineerprogramme. Key Responsibilities Architect and govern production-grade agentic systems at enterprise scale: multi-agent orchestration across complex environments, RAG pipelines, policy-based routing, memory management, andprogramme-level lifecycle observability Define RAG pipeline standards across engagements:establishchunking and embedding strategies, set quality benchmarks, and ensure … production depth, not tutorial level Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code: provider abstraction, token management,latencyand cost tradeoffs RAG pipeline ownership: embeddings, chunking strategy, vector databases, and context engineering LLMOpsfundamentals: eval harness design, prompt versioning, and production observability Cloud-native engineering maturity: Kubernetes, Docker ...

pathway to the Forward Deployed Engineerprogramme. Key Responsibilities Architect and govern production-grade agentic systems at enterprise scale: multi-agent orchestration across complex environments, RAG pipelines, policy-based routing, memory management, andprogramme-level lifecycle observability Define RAG pipeline standards across engagements:establishchunking and embedding strategies, set quality benchmarks, and ensure … production depth, not tutorial level Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code: provider abstraction, token management,latencyand cost tradeoffs RAG pipeline ownership: embeddings, chunking strategy, vector databases, and context engineering LLMOpsfundamentals: eval harness design, prompt versioning, and production observability Cloud-native engineering maturity: Kubernetes, Docker ...

direct pathway to the Forward Deployed Engineer programme. Key Responsibilities Design and build production-grade agentic systems end-to-end: multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, memory management, and lifecycle observability Build and own RAG pipelines: embeddings, chunking strategy, vector search, context window engineering and tuning … depth, not tutorial level Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code: provider abstraction, token management, latency and cost tradeoffs RAG pipeline ownership: embeddings, chunking strategy, vector databases, and context engineering LLMOps fundamentals: eval harness design, prompt versioning, and production observability Cloud-native engineering maturity: Kubernetes ...

direct pathway to the Forward Deployed Engineerprogramme. Key Responsibilities Design and build production-grade agentic systems end-to-end: multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, memory management, and lifecycle observability Build and own RAG pipelines: embeddings, chunking strategy, vector search, context window engineering and tuning against … production depth, not tutorial level Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code: provider abstraction, token management,latencyand cost tradeoffs RAG pipeline ownership: embeddings, chunking strategy, vector databases, and context engineering LLMOpsfundamentals: eval harness design, prompt versioning, and production observability Cloud-native engineering maturity: Kubernetes, Docker ...

direct pathway to the Forward Deployed Engineerprogramme. Key Responsibilities Design and build production-grade agentic systems end-to-end: multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, memory management, and lifecycle observability Build and own RAG pipelines: embeddings, chunking strategy, vector search, context window engineering and tuning against … production depth, not tutorial level Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code: provider abstraction, token management,latencyand cost tradeoffs RAG pipeline ownership: embeddings, chunking strategy, vector databases, and context engineering LLMOpsfundamentals: eval harness design, prompt versioning, and production observability Cloud-native engineering maturity: Kubernetes, Docker ...

outcomes can be achieved. You will work across customer‐facing AI use cases including personalisation, customer decisioning, customer service agents, retrieval‐augmented generation solutions and agentic workflows. This is a senior role, but it remains technical. You will need to review architectures, challenge design … teams and ensure solutions are ready for production. What You Will Do Review and challenge solution architectures, covering model selection, retrieval‐augmented generation, agentic workflows, evaluation frameworks, guardrails, scalability and cost. Identify technical and delivery risks early, including data quality issues, integration complexity, performance ...

closely with engineers to translate validated approaches into scalable, customer-facing solutions. Key Responsibilities: Develop and implement NLP, LLM, and generative AI approaches (e.g., RAG, prompt strategies, patent search). Define agentic workflows and reasoning strategies for multi-step IP tasks. Develop retrieval strategies, including hybrid search (semantic … Strong experience designing and running experiments, including model evaluation and iteration. Strong coding skills in Python. Experience with generative AI techniques (e.g., prompt engineering, RAG). Experience designing and evaluating hybrid search (semantic + lexical) using embeddings and vector databases. Experience designing agentic workflows and reasoning strategies, with hands ...

Tech Lead level, with the ability to be both highly technical and an effective people manager Hands‐on experience building AI/ML applications (RAG, agent frameworks, MCPs, skills, harnesses) and taking them to production or in platforming (LLM or MCP gateway, agentic runtime, auth, data retrieval, eval … About The Team Our AI Strategy and Innovation team shapes Moody's product ecosystem through AI, data, and strategic partnerships to deliver next‐generation solutions. The team embeds AI across product strategy using large language models, agentic platforms, and advanced analytics to enhance decision‐making and client outcomes. ...

Tech Lead level, with the ability to be both highly technical and an effective people manager Hands-on experience building AI/ML applications (RAG, agent frameworks, MCPs, skills, harnesses) and taking them to production or in platforming (LLM or MCP gateway, agentic runtime, auth, data retrieval, eval … About the Team Our AI Strategy and Innovation team shapes Moody's product ecosystem through AI, data, and strategic partnerships to deliver next-generation solutions. The team embeds AI across product strategy using large language models, agentic platforms, and advanced analytics to enhance decision-making and client outcomes. ...

Tech Lead level, with the ability to be both highly technical and an effective people manager Hands-on experience building AI/ML applications (RAG, agent frameworks, MCPs, skills, harnesses) and taking them to production or in platforming (LLM or MCP gateway, agentic runtime, auth, data retrieval, eval … About the Team Our AI Strategy and Innovation team shapes Moody's product ecosystem through AI, data, and strategic partnerships to deliver next-generation solutions. The team embeds AI across product strategy using large language models, agentic platforms, and advanced analytics to enhance decision-making and client outcomes. ...

Tech Lead level, with the ability to be both highly technical and an effective people manager Hands-on experience building AI/ML applications (RAG, agent frameworks, MCPs, skills, harnesses) and taking them to production or in platforming (LLM or MCP gateway, agentic runtime, auth, data retrieval, eval … technical direction Our AI Strategy and Innovation team shapes Moody's product ecosystem through AI, data, and strategic partnerships to deliver next-generation solutions. The team embeds AI across product strategy using large language models, agentic platforms, and advanced analytics to enhance decision-making and client outcomes. ...

tools within the work environment) to improve delivery speed, code quality, and operational outcomes at scale (e.g., AI-driven PR review assistance, test generation/maintenance, release readiness checks, incident triage and root-cause acceleration), while defining guardrails for validation, security, resiliency, and reuse across teams. Applies knowledge … multiple modern programming languages including Python, Golang, TypeScript and similar technologies in an AWS/Cloud environment. Experience in the use of GPT, LLM, RAG, Gen AI, Prompt Engineering related technologies Experience in developing, debugging, and maintaining code in a large corporate environment with one or more modern programming languages ...

reliability, innovation and engineering excellence. Your impact As a Technical Leader, you will drive the architectural vision and implementation of our next-generation AI-powered Production Intelligence platform. You will combine Site Reliability Engineering practices with modern agentic AI (reusable Skills, Model Context Protocol (MCP), and LLM tooling … management, and automated RCA. Preferred Qualifications AI & Agentic Systems: Hands‐on experience building LLM pipelines, AI Agents, Model Context Protocol (MCP) servers/clients, RAG architectures, and evaluation frameworks. Observability & Telemetry: Experience with OpenTelemetry (OTel), Prometheus, Grafana, Splunk, ThousandEyes, or distributed tracing systems. Cloud & Infrastructure: Expertise in public cloud providers ...

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. ...

build business cases, and define practical implementation roadmaps. Provide technical leadership across AI technologies Lead across modern AI architectures, Generative AI, Agentic AI, LLMs, RAG, Data Platforms, Cloud AI Services, and enterprise integration patterns. Remain hands‐on where required Lead solution architecture, technical assurance, innovation leadership, and support the resolution … consultants, architects, data specialists, and AI engineers, fostering innovation and continuous learning. Essential skills AI technical depth Generative AI, Agentic AI, Machine Learning, LLMs, RAG, MLOps, Enterprise AI Architecture, AI Risk Management & Compliance. Governance and operating models AI Strategy, AI Governance, Responsible AI Frameworks, and AI Operating Models. Data foundations ...

audits within Tech teams to assess quick‐win candidates, needs for architect‐level guidance, and non‐worth‐pursuing cases. Create technical training content on RAG, AI agent design, prompt engineering, and API integration for a Tech audience. Provide floor support during workshops, including live debugging and troubleshooting. Governance, Security & Process … DevOps) with a subsequent move into enablement, consultancy, or internal transformation. Proven experience coaching technical teams to build and deploy AI agents or RAG pipelines in production. Hands‐on with at least one low‐code/no‐code automation platform (e.g., n8n). Strong prompt engineering knowledge and ability ...

including data ingestion and modelling, backend services and APIs, AI orchestration, frontend experiences, deployment, and operations. Design and build production-grade AI features, including RAG across structured and unstructured investment data, agentic workflows, document intelligence, and AI-generated analytics. Build intuitive, information-dense interfaces for investment professionals, including analytical grids … React, advanced SQL, and complex data modelling, working with both structured and unstructured data. Proven applied AI/LLM experience, shipping production solutions using RAG, embeddings/vector search, agentic workflows, evaluation frameworks, and guardrails. Hands-on cloud and infrastructure expertise across Azure and Kubernetes (AKS), including containerisation ...

Transform customer journeys and service interactions using data, CCaaS platforms and AI to create seamless and consistent experiences Contribute to building and delivery of RAG pipelines, multi-agent orchestration and eval frameworks for enterprise-scale AI deployments Be a technical advisor Support client teams on AI architecture decisions, platform selection … regulated environments. Core experience Strong engineering background with production experience in Python and similar languages across AI systems Experience building or contributing to RAG pipelines, multi-agent systems or LLM-based products, ideally at meaningful scale Hands-on experience with at least one major cloud AI platform (AWS Bedrock ...

Transform customer journeys and service interactions using data, CCaaS platforms and AI to create seamless and consistent experiences Contribute to building and delivery of RAG pipelines, multi‐agent orchestration and eval frameworks for enterprise‐scale AI deployments Be a technical advisor Support client teams on AI architecture decisions, platform selection … regulated environments. Core experience Strong engineering background with production experience in Python and similar languages across AI systems Experience building or contributing to RAG pipelines, multi‐agent systems or LLM‐based products, ideally at meaningful scale Hands‐on experience with at least one major cloud AI platform (AWS Bedrock ...

mainly Python across the modern AI engineering stack - harness engineering, skills and tool building, agent workflows and orchestration, agent hosting and sandboxing, guardrails, evals, RAG and context engineering, and tokenomics (cost, latency, model selection). Production-grade LLM system experience is the core requirement. You will work on three types … your primary language. LLM-powered systems in production: real-world experience working with models via APIs - harnesses, orchestration, structured output, tool use and agents, RAG where appropriate. Evals and quality: designing evaluation sets, measuring accuracy, recall and precision for LLM steps, regression-testing prompts and workflows. Safety and guardrails ...

customers Transform customer journeys and service interactions using data, CCaaS platforms and AI to create seamless and consistent experiences Build and lead delivery of RAG pipelines, multi-agent orchestration and eval frameworks for enterprise-scale AI deployments Be a trusted technical advisor Advise clients on AI architecture decisions, platform selection … environment. Core experience Strong engineering background with production experience in Python and similar languages across AI systems Proven track record of architecting and delivering RAG pipelines, multi-agent systems or LLM-based products at enterprise scale Deep hands-on experience with at least one major cloud AI platform (AWS Bedrock ...

mainly Python across the modern AI engineering stack - harness engineering, skills and tool building, agent workflows and orchestration, agent hosting and sandboxing, guardrails, evals, RAG and context engineering, and tokenomics (cost, latency, model selection). Production-grade LLM system experience is the core requirement. You will work on three types … your primary language. LLM-powered systems in production: real-world experience working with models via APIs - harnesses, orchestration, structured output, tool use and agents, RAG where appropriate. Evals and quality: designing evaluation sets, measuring accuracy, recall and precision for LLM steps, regression-testing prompts and workflows. Safety and guardrails ...

theoretically. We are already building it. We are looking for a Director, Generative AI Experience Engineering to help define and deliver the next generation of AI-native customer experiences across commerce, content and customer interfaces for some of the world’s most ambitious brands. This role sits … edge rendering - Component systems and frontend orchestration AI Ecosystems & Orchestration - Experience across modern AI ecosystems including OpenAI, Gemini, Claude and OSS models RAG pipelines, vector databases, embeddings and chunking Tool calling, agentic systems, orchestration and memory frameworks Prompt engineering, prompt management and context engineering AI observability, evaluations, governance and guardrails ...