20 of 20 Retrieval-Augmented Generation Jobs in the City of London

Senior AI Engineer (Gen AI & RAG) Greater London, England, United Kingdom (On-site) Join an award-winning, internationally recognised B2B Consultancy as a Senior AI Engineer, where you will play a central role in delivering and evolving production-grade generative AI capabilities that power real-world business outcomes. This … intelligence layer of next-generation AI products. You will architect and implement Retrieval-Augmented Generation (RAG) pipelines, agentic workflows, and rigorous evaluation frameworks that ensure AI systems are accurate, reliable, and grounded in genuine business value. Reporting to the Director ...

using Python, machine learning frameworks, and Generative AI/LLM components. Pipelines: Develop and optimize Retrieval-Augmented Generation (RAG) pipelines, vector databases, and scalable data processing streams. MLOps: Implement model deployment, monitoring, testing, and lifecycle management using standard CI/CD and containerized workflows. … role. Core Tech: Solid professional experience with Python and frameworks like PyTorch, TensorFlow, or Scikit-Learn. GenAI: Hands-on experience developing LLM-based applications, RAG pipelines, and prompt engineering. Infrastructure: Experience deploying applications in cloud environments (AWS, Azure, or GCP) using Docker and Kubernetes. Engineering: Strong software engineering fundamentals, including ...

equivalents. Ability to apply AI agents across all phases of delivery: requirements, architecture, coding, testing, documentation, and deployment. Experience with LLMs, prompt engineering, RAG, vector databases, and orchestration patterns. Strong Azure expertise preferred, with hands‐on exposure to AWS and GCP. Experience integrating AI into distributed systems, microservices, APIs ...

implementing end-to-end AI/ML solutions from development through to deployment and monitoring * Building scalable Generative AI and Agentic AI solutions, including RAG pipelines and orchestration frameworks * Implementing MLOps frameworks, governance and best practices * Translating business requirements into cloud-native AI and data architectures across Azure ...

cloud‐native delivery patterns What Will Make You Stand Out Experience building, deploying, and evaluating multi‐agent AI solutions, agent orchestration patterns, RAG architectures, and enterprise integrations Knowledge of agent communication protocols and interoperability patterns, such as MCP and A2A Ability to balance innovation with practical delivery considerations, including risk ...

Python and JavaScript Hands-on experience with backend frameworks and modern frontend frameworks Deep knowledge of Generative AI and agent-based AI frameworks including RAG and orchestration patterns Strong experience working with vector databases and AI-specific data stores Solid understanding of AI and ML models, LLMs and generative ...

GitHub, Kubernetes, containerisation or equivalent enterprise DevOps platforms. Experience supporting AI, machine learning, data science, analytics or automation teams. Experience with LLM application architecture, RAG, vector stores, orchestration frameworks, model APIs or context management. Experience integrating third‐party or public data APIs into enterprise environments. Experience defining platform operating models ...

coding standards and best practices Guide evaluation and safety approaches Support production deployments and troubleshooting Hands-on Skills Required Design multi-agent solutions Design RAG architecture Implement complex orchestration workflows Build scalable AI microservices Define AI governance patterns Troubleshoot production AI solutions ...

analytical reasoning. Exceptional communication and collaboration skills. Experience with ML frameworks such as TensorFlow, PyTorch, TensorRT, or ONNX. Experience with Large Language Models, including RAG and fine-tuning techniques. Familiarity with compute infrastructure necessary to support operating AI and ML technology. For more information about DRW's processing activities ...

pipeline experience AI Tooling: Hands‐on experience integrating LLMs, handling vector databases, and building robust chunking/embedding strategies Secure Architecture: Deploying LLM pipelines, RAG systems, and orchestration layers within secure, classification‐bound environments Local Implementations: Self-hosting, optimising, and containerising open‐source models (e.g., Llama, Mistral) on private ...

Delivery: Design, build, and deploy AI‐powered applications (chatbots, copilots, document intelligence, decision‐support tools) for insurance use cases; implement Retrieval‐Augmented Generation patterns; build LLM‐based workflows and agents. Cloud & Platform Engineering (GCP): Deploy solutions on GCP leveraging Vertex AI, BigQuery, Cloud … Generative AI & LLMs: Hands‐on experience with ChatGPT/OpenAI APIs and/or Anthropic Claude; prompt engineering, system prompts, evaluation techniques; implementation of RAG, vector databases, semantic search. Cloud Platforms: Strong experience with GCP, especially Vertex AI; Docker/containerised workloads; cloud security, IAM, cost management. Data & AI Tooling ...

working with technologies including Azure Databricks, Azure Machine Learning, Azure AI Foundry, LangChain, LangGraph and Python, building enterprise AI applications using RAG, vector databases, prompt orchestration and tool-calling patterns. You'll need experience with: Deploying LLMs and machine learning models into Azure enterprise environments. Azure Databricks, Azure Machine Learning … ideally Azure AI Foundry. Building production AI applications using LangChain, LangGraph and Python. MLOps/LLMOps including deployment, monitoring, governance and lifecycle management. RAG, vector databases, prompt engineering and tool-calling patterns. Building end-to-end AI/ML pipelines from data preparation through to production. Working with technical ...

highly regulated environments Strong understanding of software architecture and API design IT WOULD BE NICE FOR THE AI SOFTWARE ENGINEER TO HAVE. Experience with RAG pipelines and vector databases Knowledge of MLOps tooling and CI/CD pipelines Exposure to Palantir Foundry or similar data platforms Experience working on National … Engineer/Machine Learning Engineer/LLM Engineer/Python/AWS/Azure/Docker/Kubernetes/Generative AI/NLP/RAG/MLOps/UKSV DV/Outside IR35/London ...

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 ...

Skills for the Artificial Intelligence Architect: Proven experience architecting solutions across Generative AI, Agentic AI, machine learning and automation Strong understanding of prompt engineering, RAG pipelines, model tuning, MLOps and LLMOps Experience delivering enterprise‐scale RAG solutions using LLMs and vector databases Ability to design AI platforms that integrate with ...

booking and customer-service platforms * Automate customer enquiries, lead qualification, booking support and follow-up communications * Build solutions using OpenAI APIs, large language models, RAG, embeddings, vector search and tool calling * Implement permissions, monitoring, escalation processes and data-privacy controls * Integrate third-party systems using APIs, webhooks and data pipelines … WordPress websites, including custom themes, plugins and API integrations * Experience integrating booking engines, ecommerce platforms and payment systems * Practical experience with OpenAI APIs, LLMs, RAG and agentic workflows * Experience integrating CRM platforms, WhatsApp Business, webhooks and third-party APIs * Strong SQL, data-integration and dashboard-development skills * Knowledge of technical ...

booking and customer-service platforms * Automate customer enquiries, lead qualification, booking support and follow-up communications * Build solutions using OpenAI APIs, large language models, RAG, embeddings, vector search and tool calling * Implement permissions, monitoring, escalation processes and data-privacy controls * Integrate third-party systems using APIs, webhooks and data pipelines … WordPress websites, including custom themes, plugins and API integrations * Experience integrating booking engines, ecommerce platforms and payment systems * Practical experience with OpenAI APIs, LLMs, RAG and agentic workflows * Experience integrating CRM platforms, WhatsApp Business, webhooks and third-party APIs * Strong SQL, data-integration and dashboard-development skills * Knowledge of technical ...

Doing Rapidly prototype, build and validate new AI-driven solutions, taking concepts from idea to working demo in days. Develop components using LLMs, RAG, prompt engineering and modern agent frameworks . Work closely with architects, product leaders and engineers to de-risk emerging technologies and shape future solutions. Leverage … Strong software engineering experience with C#/.NET Core, Angular/TypeScript and Python . Practical experience working with AI technologies including LLMs, RAG, agent frameworks and prompt engineering . A track record of rapidly building prototypes, MVPs and proof-of-concepts. Experience within insurance, reinsurance, risk analytics or financial ...

reusable agent components and playbooks Proactively surface new automation opportunities across the business Key Skills Python & LLM agent frameworks (LangChain, CrewAI, LlamaIndex) Prompt engineering & RAG pipelines Business analysis & stakeholder management Process mapping & workshop facilitation Microsoft 365 & Microsoft Copilot No-code/low-code tooling (Zapier, Make) Desirable Skills Experience … etc. Strong enough technically to assess feasibility and scope what is buildable; commercially sharp enough to prioritise what is worth building. Familiarity with LLMs, RAG pipelines, tool/function calling, and integrating AI into real business workflows. Proven ability to lead discovery workshops and translate complex business problems into clear ...

doing Owning the firms GenAI platform deployment, maintenance, optimisation, and vendor relationships Building AI-backed applications including assistants, copilots, agents and document workflows Implementing RAG capabilities and integrating LLMs via APIs and SDKs Managing AI governance acceptable use, auditability, risk mitigation (prompt injection, data leakage, hallucination) Monthly reporting on model … ideally in legal or professional services Strong working knowledge of the major foundational models GPT, Gemini, Claude, Llama Hands-on experience with prompt engineering, RAG, and LLM API/SDK integration Understanding of AI risk and security you know what prompt injection looks like and how to defend against ...