1 to 25 of 76 Retrieval-Augmented Generation Jobs in London

will own and drive large portions of our AI agent infrastructure, from designing and deploying multi-agent systems to integrating Retrieval-Augmented Generation (RAG) pipelines, model fine-tuning, and evaluation frameworks. You will be responsible for delivering AI-powered features into production at scale - ensuring they are performant, reliable, and secure - while also contributing … monitoring solutions. Contribute to infrastructure planning, deployment, and optimization in cloud environments (AWS, GCP, or Azure). Develop and deploy AI-powered features in production, including RAG (Retrieval-Augmented Generation) systems, multi-agent infrastructure, and evaluation frameworks (Evals). Build real-world AI use cases by integrating fine-tuned models and large language model … queues (Celery, RQ, etc.). Proficiency with Redis for caching, pub/sub, or job queues. Hands-on experience building and deploying AI applications in production environments. Experience implementing RAG pipelines , AI agent orchestration , model fine-tuning , and performance monitoring. Familiarity with LLM evaluation techniques and tools for measuring model accuracy, reliability, and safety. What We Offer: You will be More ❯

Responsibilities Architect Autonomous Agents: Design and implement robust, goal-driven AI agents using leading frameworks like LangChain, LangGraph, and the Google Agent Development Kit (ADK). Develop and Evaluate RAG Pipelines: Engineer and optimize end-to-end Retrieval-Augmented Generation (RAG) systems, including data ingestion, chunking strategies, and implementing rigorous pipeline evaluation frameworks for … Kit (ADK) LLM Expertise: Advanced Prompt Engineering and hands-on experience with model fine-tuning techniques including PEFT and QLoRA. Proven experience with models like Gemini, and Llama 3. RAG & Vector Databases: Deep expertise in RAG architecture and evaluation metrics. Proven experience with Vector Databases such as Milvus, Pinecone, or Chroma. Software & Cloud Engineering: Programming & APIs: Expert-level Python and More ❯

Responsibilities Architect Autonomous Agents: Design and implement robust, goal-driven AI agents using leading frameworks like LangChain, LangGraph, and the Google Agent Development Kit (ADK). Develop and Evaluate RAG Pipelines: Engineer and optimize end-to-end Retrieval-Augmented Generation (RAG) systems, including data ingestion, chunking strategies, and implementing rigorous pipeline evaluation frameworks for … Kit (ADK) LLM Expertise: Advanced Prompt Engineering and hands-on experience with model fine-tuning techniques including PEFT and QLoRA. Proven experience with models like Gemini, and Llama 3. RAG & Vector Databases: Deep expertise in RAG architecture and evaluation metrics. Proven experience with Vector Databases such as Milvus, Pinecone, or Chroma. Software & Cloud Engineering: Programming & APIs: Expert-level Python and More ❯

Responsibilities Architect Autonomous Agents: Design and implement robust, goal-driven AI agents using leading frameworks like LangChain, LangGraph, and the Google Agent Development Kit (ADK). Develop and Evaluate RAG Pipelines: Engineer and optimize end-to-end Retrieval-Augmented Generation (RAG) systems, including data ingestion, chunking strategies, and implementing rigorous pipeline evaluation frameworks for … Kit (ADK) LLM Expertise: Advanced Prompt Engineering and hands-on experience with model fine-tuning techniques including PEFT and QLoRA. Proven experience with models like Gemini, and Llama 3. RAG & Vector Databases: Deep expertise in RAG architecture and evaluation metrics. Proven experience with Vector Databases such as Milvus, Pinecone, or Chroma. Software & Cloud Engineering: Programming & APIs: Expert-level Python and More ❯

Responsibilities Architect Autonomous Agents: Design and implement robust, goal-driven AI agents using leading frameworks like LangChain, LangGraph, and the Google Agent Development Kit (ADK). Develop and Evaluate RAG Pipelines: Engineer and optimize end-to-end Retrieval-Augmented Generation (RAG) systems, including data ingestion, chunking strategies, and implementing rigorous pipeline evaluation frameworks for … Kit (ADK) LLM Expertise: Advanced Prompt Engineering and hands-on experience with model fine-tuning techniques including PEFT and QLoRA. Proven experience with models like Gemini, and Llama 3. RAG & Vector Databases: Deep expertise in RAG architecture and evaluation metrics. Proven experience with Vector Databases such as Milvus, Pinecone, or Chroma. Software & Cloud Engineering: Programming & APIs: Expert-level Python and More ❯

ensuring robust versioning, monitoring, and adherence to best practices. Drive the integration of external knowledge bases and retrieval systems to augment LLM capabilities. Research and Development: Effective RAG architectures and technologies for organizing complex domain-specific data (e.g. vector databases, knowledge graphs) and effective knowledge extraction. Explore and benchmark state-of-the-art LLMs, tuning, adaptation, and training … technical projects to successful completion in agile environments. Strong communication skills to align technical solutions with business goals. Ability to mentor and foster innovation within the team. LLM and RAG Expertise: Strong expertise in building Retrieval-Augmented Generation (RAG) architectures and integrating with vector and graph databases. Transformer and LLM Architectures: In-depth experience More ❯

projects, driving timelines, and delivering high-quality results in fast-paced environments. Bonus Experience in deploying multi-agent frameworks and retrieval-augmented generation (RAG) pipelines. Familiarity with regulatory and privacy considerations in healthcare AI applications. IQVIA is a leading global provider of clinical research services, commercial insights and healthcare intelligence to the life sciences More ❯

projects, driving timelines, and delivering high-quality results in fast-paced environments. Bonus: Experience in deploying multi-agent frameworks and retrieval-augmented generation (RAG) pipelines. Familiarity with regulatory and privacy considerations in healthcare AI applications. IQVIA is a leading global provider of clinical research services, commercial insights and healthcare intelligence to the life sciences More ❯

Generative AI and Search - Artificial Intelligence Location: London Business Area: Engineering and CTO Ref #: Responsibilities Developing and deploying robust Retrieval-Augmented Generation (RAG) systems, curating high-quality data for model training and evaluation, and building evaluation frameworks to enable rapid iteration and continuous improvement based on real-world user interactions. Designing and implementing More ❯

personal and professional development! Requirements: Strong Python scripting skills Strong understanding of LLMs Experience delivering Gen-AI projects Experience with Retrieval-Augmented Generation (RAG) Experience with Microsoft data technologies would be beneficial Experience with Cloud platforms - ideally Azure Strong communication, stakeholder management and problem-solving skills Benefits: Salary of up to around More ❯

personal and professional development! Requirements: Strong Python scripting skills Strong understanding of LLMs Experience delivering Gen-AI projects Experience with Retrieval-Augmented Generation (RAG) Experience with Microsoft data technologies would be beneficial Experience with Cloud platforms - ideally Azure Strong communication, stakeholder management and problem-solving skills Benefits: Salary of up to around More ❯

with a focus on leveraging AI/GAI technologies and large language models (LLMs) Advanced AI Integration : Apply experience with retrieval-augmented generation (RAG), vector databases (e.g. Pinecone, Weaviate, FAISS), and enterprise search for AI-driven knowledge discovery Optimize AI Performance : Utilize practical experience designing structured prompts, fine-tuning models, and cost optimization strategies More ❯

TensorFlow, and specialised Generative AI libraries (LangChain, LangGraph or related open-source toolkits strongly preferred. Background in Traditional ML/AI is preferred. Deep understanding of LLMs, prompt engineering, RAG pipelines, vector databases, and generative architectures; related security practices and evaluation procedures; hands-on experience fine-tuning, deploying and evaluating large-scale production systems. Hands-on experience designing and implementing More ❯

accuracy and trust. Responsibilities: Fine-tune and optimize foundation models (e.g., LLaMA, FinBERT) for financial text and transaction data. Build retrieval-augmented generation (RAG) pipelines with Hugging Face, Lang Chain, and vector databases. Implement human-in-the-loop systems to continuously validate, improve, and govern AI outputs. Deploy and monitor ML models in production More ❯

with enterprise partners. No two weeks will look the same. Fine-tune and privately deploy LLMs - with a focus on Retrieval-Augmented Generation (RAG) pipelines Build and scale computer vision systems - from object detection to image segmentation Apply NLP to real-world business problems - summarisation, entity recognition, information extraction, and more Train and deploy More ❯

dependable and consistent results Create and implement intelligent workflow systems, integrating LLMs with enterprise applications, APIs, and automation ecosystems Develop Retrieval-Augmented Generation (RAG) architectures to connect organisational knowledge with LLMs Rapidly prototype and refine AI applications, showcasing tangible business benefits Provide guidance on ethical AI implementation, covering governance frameworks, regulatory compliance, and risk … JavaScript for rapid prototyping and system integration Familiarity with workflow automation solutions (UiPath, Power Automate, Zapier, n8n) and API development Practical knowledge of vector databases and embedding technologies for RAG system implementation Outstanding interpersonal skills - capable of converting business challenges into technical AI strategies Background in agile methodologies or dynamic project environments **Please only apply for this role if you More ❯

dependable and consistent results Create and implement intelligent workflow systems, integrating LLMs with enterprise applications, APIs, and automation ecosystems Develop Retrieval-Augmented Generation (RAG) architectures to connect organisational knowledge with LLMs Rapidly prototype and refine AI applications, showcasing tangible business benefits Provide guidance on ethical AI implementation, covering governance frameworks, regulatory compliance, and risk … JavaScript for rapid prototyping and system integration Familiarity with workflow automation solutions (UiPath, Power Automate, Zapier, n8n) and API development Practical knowledge of vector databases and embedding technologies for RAG system implementation Outstanding interpersonal skills - capable of converting business challenges into technical AI strategies Background in agile methodologies or dynamic project environments **Please only apply for this role if you More ❯

third-party services. Develop front-end interfaces using JavaScript and frameworks such as React. Build and deploy Agentic systems and Retrieval-Augmented Generation (RAG) systems with Large Language Models (LLMs). Participate in privacy automation programs, including workflows for user approvals and reviews. Implement and maintain CI/CD pipelines in Jenkins to streamline More ❯

time management skills. Bonus skills • Experience deploying and managing applications with Azure and Docker. • Familiarity with frameworks like LangChain and Retrieval-Augmented Generation (RAG) models for AI-driven applications. • Experience with pandas for data manipulation. What’s on offer • Regular salary reviews recognising performance and contribution. • Generous annual leave: 25 days plus three days More ❯

Ofcom, Openreach, independent networks and ISPs to uncover problems that directly impact how the UK connects. Advance the use of retrieval-augmented generation (RAG), combining LLMs with vector search, to push the boundaries of how AI can be applied to connectivity challenges. Our stack Backend: PHP (Laravel), Python (for AI/ML workflows) Frontend More ❯

Ofcom, Openreach, independent networks and ISPs to uncover problems that directly impact how the UK connects. Advance the use of retrieval-augmented generation (RAG), combining LLMs with vector search, to push the boundaries of how AI can be applied to connectivity challenges. Our stack Backend: PHP (Laravel), Python (for AI/ML workflows) Frontend More ❯

designing and managing databases in Postgres. AI/ML Expertise: Build and deploy Agentic systems, MCP servers/clients, and Retrieval-Augmented Generation (RAG) systems with Large Language Models (LLMs). Extract, transform, and load (ETL) data to build vector databases with embedding models. DevOps and Maintenance: Implement CI/CD pipelines to streamline More ❯

experience Solid expertise in Node.js Experience integrating LLM APIs and open-source models into production systems Hands-on work implementing Retrieval-Augmented Generation (RAG) pipelines Experience designing and optimizing agentic AI workflows Tremendous opportunity offering plenty of scope for career progression in a friendly, innovative environment where you'll be able to bring ideas More ❯

features in complex business contexts Strong understanding of machine learning algorithms, NLP, and LLMs with demonstrated business application expertise Experience developing AI-powered automation systems, intelligent assistants/copilots, RAG systems, voice interfaces, and computer vision applications (image and video processing) for enterprise environments Knowledge of advanced AI agent frameworks and architectures such as ReAct for building more effective autonomous More ❯

experience). Nice-to-Have Production experience integrating Microsoft Word (Office.js) add-ins with backend services; knowledge of M365 auth patterns. Hands-on experience with LLM/AI platformization (RAG, vector search, evals, safety/guardrails). Experience with FinOps practices and infrastructure cost management. Prior exposure to global scaling challenges (latency, data residency, multi-region deployments). What We More ❯