126 to 150 of 186 Retrieval-Augmented Generation Jobs in the UK

applications using Copilot Studio (Full), Power Platform, Dynamics 365, and Azure AI; establish security, governance, and performance baselines. Design and implement LLM-powered solutions (RAG, prompt engineering, grounded generation) with data governance, telemetry, and quality monitoring (LLMOps). Integrate Microsoft 365 and Dynamics 365 with enterprise systems ...

storage and search systems (e.g. pgvector, Pinecone, Azure Search), as well as experience working with graph technologies like Neo4j Practical understanding of retrieval-augmented generation pipelines and how to implement structured outputs or link models to graph-based knowledge systems Track record of optimising ...

What We're Looking For Must-Haves: 4+ years experience writing production ready code for machine learning systems 2+ years experience developing conversational AI, RAG, agentic systems or LLM-based products Familiarity with RAG orchestration frameworks such as LangChain or LlamaIndex.2+ Experience with production optimisation for RAG systems, including latency ...

applications providing cutting-edge scientific tooling to scientists Shape the AI strategy and technology stack Develop AI features leveraging various methodologies (e.g., LLMs, RAG, traditional ML) Design and implement data strategies for AI development and training Requirements 4+ years' experience across Fullstack development (Python/Modern JavaScript (React ...

iterative prototyping across multidisciplinary teams. Strong foundation in software development with C# and TypeScript. Experience with AI/LLM concepts (e.g., prompt engineering, RAG). Analytical mindset for assessing sufficiency (relevance, completeness, freshness) and mitigating risks like hallucinations. Focus on Clean Architecture and Clean Code principles. Familiarity with Enterprise Design ...

experience building and deploying real-world products Strong understanding of modern AI systems, including LLMs, multimodal models, agents, and supporting tooling (e.g. LangChain, RAG pipelines, SFT/RL fine-tuning) Solid infrastructure experience, including cloud platforms, containerization, and relational or graph databases Proven ability to build independently, move quickly ...

technical prioritisation across multiple workstreams Building and shipping production features using .NET, Azure, React, and modern AI frameworks Implementing Generative AI capabilities using LLMs, RAG, and agentic approaches Upholding engineering quality through code reviews, testing practices, and technical standards What you’ll bring to the table as a Lead Full ...

growing AI team , contribute to cutting-edge projects, and develop your skills with mentorship from senior engineers. You'll work on AI-powered applications, RAG pipelines, and model fine-tuning , solving real business problems. About the Role Design, implement, and fine-tune LLMs and generative AI solutions (OpenAI, Anthropic Claude … Gemini, open-source models) Build and optimize RAG pipelines , vector databases, and prompt engineering strategies Develop AI-powered applications integrating LLMs with APIs, agents, and workflows Deploy and monitor AI models on cloud platforms (Azure preferred; AWS/GCP acceptable) Collaborate with senior engineers and cross-functional teams to deliver ...

identify AI integration opportunities for productivity, quality, or innovation gains. Design, code, train, and test AI models tailored to use cases (e.g., NLP, CV, RAG, forecasting, etc.). Perform effort estimation and model validation and monitor deployment success and cost-performance trade-offs. Collaborate closely with local technical leads while … Learning , Deep Learning , Natural Language Processing , Computer Vision , Generative AI , Reinforcement Learning , LLMs (e.g., GPT, Claude, Mistral, LLaMA, DeepSeek, etc.). Agent-based architectures , RAG , prompt engineering , chatbots , classification , summarization , speech-to-text , image understanding. Cloud platforms (AWS, Azure, GCP). ML Ops tools and deployment workflows. AI-assisted development ...

Engineer - LLM RAG AWS MLOps – Bristol (Hybrid) I'm working with a fast-growing tech company in Bristol that needs an AI/ML Engineer to build and deploy machine learning and LLM solutions. You'll be working across the full ML lifecycle—from design through to production … doing: Building and deploying ML models and LLM applications Fine-tuning large language models for specific use cases Working with prompt engineering and RAG systems Creating end-to-end ML pipelines—ingestion, feature engineering, deployment Developing LLM-powered tools: chatbots, automation, content generation Implementing MLOps practices: versioning, experiment ...

React.js + Node.js 100% Remote (UK-based only) Desirable Skills Knowledge of SQL or React Experience with AI/LLMs or RAG (Retrieval-Augmented Generation) Familiarity with integration testing Exposure to multiple programming languages beyond TypeScript Daily use of AI coding assistants Strong problem ...

environments. Deep understanding of AI governance, ethics, guardrails, compliance , and data privacy. Experience building or deploying LLM-powered systems , agentic workflows, and code-generation pipelines. Strong capability in code review, automated testing, and maintaining quality across AI-assisted codebases. Exceptional communication and stakeholder … engagement abilities—comfortable presenting to leadership. Ability to manage multiple initiatives with attention to detail and strategic alignment. Nice-to-Have Skills Exposure to RAG frameworks, vector databases, embeddings, and graph/temporal data systems. Familiarity with cloud-based deployment (AWS/Azure), containerization, and observability tooling. Experience with prompt ...

applications, covering prompt testing, output quality metrics and agent behaviour validation. ● Apply relevant AI technologies as needed, including retrieval systems (RAG, GraphRAG), knowledge graphs, vector databases or data pipelines. Role Requirements Work Experience ● At least five years as a software engineer on commercial platforms, with demonstrable experience building … Agent-to-Agent (A2A). ● LLM evaluation tooling (OpenAI Evals, LangSmith, custom evaluation harnesses). ● Advanced agent patterns: multi-agent systems, supervision, delegation strategies. ● RAG, GraphRAG and knowledge graph design and implementation. ● Vector databases and similarity search systems. ● Graph databases (ArangoDB, Neo4j, Neptune) and property graph modelling. ● Data engineering ...

team, you will have the opportunity to collaborate with industry experts, contribute to innovative projects, and play a key role in shaping next-generation GenAI solutions within a dynamic and supportive environment. We value curiosity, adaptability, and a passion for leveraging cutting-edge technologies to address real-world … Qualifications Proven experience with Databricks, including Unity Catalog, MLflow, Mosaic AI and Delta Live Tables. Strong understanding of Generative AI concepts, including LLMs, RAG, embeddings, and prompt tuning. Experience with vector databases and embedding models. Familiarity with cloud platforms (Azure preferred) and CI/CD pipelines. Excellent problem-solving ...

multi-agent collaboration Develop and optimize AI/ML models for performance, scalability, and efficiency Build advanced solutions using LangChain for agent-based and RAG systems Integrate AI capabilities using Google ADK within enterprise-grade cloud environments Stay up to date with the latest advancements in AI/ML technologies … solutions. Your Profile Key skills/knowledge/experience: Hands-on experience with Agentic AI workflows and autonomous agents Advanced proficiency in LangChain and RAG systems Expertise in Google ADK and GCP cloud services Strong programming skills in Python (and optionally R or Java) Extensive experience with AI/ ...

pipelines, and API services Develop sophisticated prompt engineering strategies for LLM-based features, including few-shot learning, chain-of-thought reasoning, and retrieval-augmented generation Optimize models for specific use cases and performance requirements Design and optimize database schemas for relational database Collaborate with ...

architectures, and emerging best practices. What you’ll bring: Expertise in AI and Machine Learning, including agent-based AI, RAG (Retrieval Augmented Generation), multi-agent systems and conversational agents. Strong programming skills in Python, Java or .NET. Experience with GenAI and LLMs (e.g. ChatGPT ...

work on developing & implementing AIML Solutions for Test Automation in the Securities Processing space. This will entail building AIML Solutions for Test Generation, Test Prioritization, Defect Triage/Reporting, Code Coverage, Framework Migration/Setup. The role requires experience in AIML(LLMs, Gen AI & Agentic AI) & Python. … aspects of AIML & Software Development including: Knowledge of AIML & Python is must. Ability to develop and implement Generative AI & Retrieval Augmented Generation solutions focused on software testing. Experience with Large Language Models(GPT, Claude). Hands- on experience with GitHub Copilot. Must ...

powered Predictive Intelligence Platform for corporates and financial institutions. Their technology connects market events, client data, and emerging opportunities through advanced agentic AI and RAG-based systems, helping financial institutions anticipate client needs before they arise. They have built a live MVP in record time, with enterprise client demos underway … lead the design and productionisation of the company’s core AI systems. You will architect, implement, evaluate, and scale RAG pipelines, agentic workflows, and LLM-based intelligence frameworks, driving real-world impact across financial markets. The role is approximately 80% hands-on and 20% strategic, covering Python engineering, system architecture ...

Responsibilities Data & Retrieval Build robust ingestion pipelines for PDFs/Word/Excel/Audio/JSON and semi-structured sources. Design RAG systems: chunking strategies, document schemas, metadata, hybrid/dense retrieval, re-ranking, and grounding. Manage vector/keyword indexes (e.g., Azure AI Search … tracing/telemetry (OpenTelemetry, LangSmith), metrics, logs, cost and token usage monitoring, alerts. Apply evaluation & QA: regression suites, offline eval sets/golden data, RAG evals (faithfulness, answer relevance, citation correctness), A/B tests, win-rate testing. Ensure reliability: rate-limit handling, retries/backoff, idempotency, circuit breakers, caching ...

controls Experience with experiment tracking and MLOps tooling (MLflow, Weights & Biases, Data Version Control) Experience developing LLM/GenAI applications, including prompt engineering and RAG architectures It Would Be Great If You Also Had Experience In Some Of These, But If Not Well Help You With Them Experience with advanced … techniques: agents, tool use, and agentic workflows Experience with vector databases (Pinecone, Weaviate, pgvector) for RAG applications Experience with feature stores (Feast, AWS Feature Store) Experience with containerisation (Docker) and orchestration (Kubernetes, ECS) Familiarity with Infrastructure as Code (Terraform, CloudFormation) Experience with data processing frameworks (Spark, Dask) for large-scale ...

tangible commercial and operational value. A focus of the role will be accelerating the organisation’s Generative AI capability, building LLM-driven tools and RAG-based solutions that unlock natural language interaction with business data. Key Responsibilities Collaborate with stakeholders across the business to capture requirements and translate them into … technical audiences. Integrate data science outputs into wider BI products and operational workflows. Develop and deploy GenAI solutions, including LLM Q&A, RAG frameworks and multi-agent systems. Contribute to high coding standards, documentation, knowledge sharing and code reviews. Stay ahead of emerging data science and AI advancements to identify ...

create meaningful impact. Key Responsibilities: Design and implement AI workflows and models for performance and scalability. Build solutions using LangChain for agent-based and RAG systems. Optimize and scale AI/ML models for efficiency. Apply prompt engineering techniques to improve AI outputs. Collaborate with cross-functional teams to translate …/ML projects. Excellent problem-solving and analytical skills. Strong communication and collaboration abilities. Desirable skills/knowledge/experience: Familiarity with LangChain and RAG systems. Experience with public cloud platforms (e.g., Google Cloud, Azure). Knowledge of prompt engineering techniques. Exposure to multi-agent orchestration frameworks. Understanding of ethical ...

Journey and broader Azure AI-related questions. Designing and delivering custom AI solutions on Azure OpenAI Service and Microsoft Foundry, using patterns like RAG, function calling, tool/agent orchestration, and fine-tuning where appropriate. Implementing MCP-based integrations between AI services and existing application components (web apps, APIs, data … Design and optimize data pipelines that prepare structured and unstructured data for model training and RAG solutions. Implement vector search, embeddings, and retrieval-augmented generation workflows. Fine-tune or customize foundation models for domain-specific use cases. Create automated evaluation and monitoring systems ...

Face APIs) into internal tools and customer-facing applications. Design and implement workflows powered by AI, such as content summarization, support automation, documentation generation, or intelligent query handling. Develop prompt chains and prompt strategies for specific business functions (engineering assistance, product support, operational efficiency). Collaborate with cross … search tools. Experience building internal tooling or developer productivity enhancements using AI. Exposure to customer support AI tools or RAG (retrieval augmented generation) systems. Why Join Paydock? Work with a passionate, remote-first team that's reshaping payments. Opportunity to lead and define ...