1 to 25 of 27 Permanent Retrieval-Augmented Generation Jobs in the Thames Valley

scalable AI services and data processing solutions using Python and related technologies. Build and maintain Retrieval-Augmented Generation (RAG) solutions and vector database architectures. Develop real-time AI applications, including speech-to-text and streaming AI interaction capabilities. Integrate AI capabilities with existing backend … technologies such as Pinecone, Weaviate, FAISS, or Azure AI Search. Experience building and supporting Retrieval-Augmented Generation (RAG) solutions. Experience working with OpenAI and other modern AI platforms. Expertise in prompt engineering, prompt evaluation, and optimisation techniques. Experience developing real-time AI and audio ...

production-grade LLM applications Commercial experience developing Generative AI and Agentic AI solutions Experience with Retrieval-Augmented Generation (RAG) architectures and vector databases Experience with AI orchestration frameworks such as LangChain, Semantic Kernel, AutoGen, or similar Experience designing, evaluating, and optimising prompts for Large … Implementing AI orchestration using modern frameworks and the Model Context Protocol (MCP) Designing and implementing Retrieval-Augmented Generation (RAG) solutions using vector databases Building scalable AI services and data processing pipelines using Python Developing real-time AI applications, including streaming and speech-enabled solutions ...

language) AI coding tools: GitHub Copilot, Cursor or equivalents Prompt engineering and context design patterns Retrieval-augmented generation (RAG), vector search, embeddings (desirable) Evaluation frameworks and automated quality pipelines for AI outputs Technical and Professional Expertise Solid production experience with C# .NET, including working … results to improve quality. Daily fluency with AI coding tools such as GitHub Copilot, Cursor or equivalents. Preferred Qualifications and Experience Retrieval-augmented generation, agentic workflows, tool use, vector search or embeddings in production settings. Experience with LLM APIs across more than one provider ...

understanding of generative AI and the modern AI stack, including large language models, prompt engineering, retrieval-augmented generation (RAG), vector databases, evaluation/monitoring and MLOps principles, with the ability to shape investment cases and operating models at scale.Extensive experience providing executive oversight ...

Master prompt engineering, learning how to craft effective prompts for controlling AI outputs. Step 9 – Retrieval-Augmented Generation (RAG) Learn how to integrate external knowledge into AI systems using RAG techniques and vector databases. Step 10 – AI Specialised Customer Service Chatbot Project Combine prompt … engineering and RAG to build an AI-powered customer service chatbot, delivering intelligent responses using vector databases and knowledge bases. Step 11 – Machine Learning Fundamentals Understand machine learning principles and algorithms, and how to train and test models using scikit-learn. Step 12 – Machine Learning Project Put your machine learning ...

Master prompt engineering, learning how to craft effective prompts for controlling AI outputs. Step 9 – Retrieval-Augmented Generation (RAG) Learn how to integrate external knowledge into AI systems using RAG techniques and vector databases. Step 10 – AI Specialised Customer Service Chatbot Project Combine prompt … engineering and RAG to build an AI-powered customer service chatbot, delivering intelligent responses using vector databases and knowledge bases. Step 11 – Machine Learning Fundamentals Understand machine learning principles and algorithms, and how to train and test models using scikit-learn. Step 12 – Machine Learning Project Put your machine learning ...

Master prompt engineering, learning how to craft effective prompts for controlling AI outputs. Step 9 – Retrieval-Augmented Generation (RAG) Learn how to integrate external knowledge into AI systems using RAG techniques and vector databases. Step 10 – AI Specialised Customer Service Chatbot Project Combine prompt … engineering and RAG to build an AI-powered customer service chatbot, delivering intelligent responses using vector databases and knowledge bases. Step 11 – Machine Learning Fundamentals Understand machine learning principles and algorithms, and how to train and test models using scikit-learn. Step 12 – Machine Learning Project Put your machine learning ...

systems in production environments, including performance tuning and cost optimization. Design and build Retrieval-Augmented Generation (RAG) systems using embeddings, vector databases, and semantic search. Build and optimize prompts and interaction strategies for LLMs to achieve desired outcomes in agentic systems. Integrate various tools … multi-agent systems. Familiarity with AI workflow orchestration and agentic frameworks (e.g., LangChain, LangGraph, Crew AI, Haystack, or similar). Practical experience with RAG architectures, embeddings, vector databases, and semantic search. Experience working with Model Context Protocol (MCP) Servers. Experience with RESTful APIs and integrating external services. Solid understanding ...

production software-engineering skills.Experience developing, integrating and operating enterprise software or AI applications.Practical understanding of LLMs, agentic AI, tool calling and retrieval-augmented generation.Experience building APIs, services and data pipelines, with Docker and cloud or on-premises deployments.Understanding of authentication, networking, access control and enterprise security.Experience ...

automated testing with pytest • Experience supporting and improving large, established production codebases, with a strong understanding of secure software development Experience with LangChain, RAG, vector databases, Azure, Entra ID, OAuth/OIDC, Redis, Terraform, Helm, Prometheus, Grafana or OpenTelemetry would be valuable but is not essential. Current SC clearance ...

API. Proven track record of delivering production software on client-facing projects, ideally within a consultancy or professional services environment. Experience with prompt engineering, RAG architectures, or agentic AI development at scale. Familiarity with AI-assisted development tools such as GitHub Copilot, Claude, and Cursor. Strong experience with Azure cloud ...

working closely with engineering, cloud and security teams to define practical controls and secure-by-design patterns. This will include areas such as LLMs, RAG, AI agents, vector databases, prompt injection, data leakage, identity, tool/API integration and AI threat modelling, alongside broader cloud and enterprise security architecture. ...

complex or ambiguous cross-functional operational challenges where requirements are not fully formed. Understanding of AI concepts (e.g. prompt engineering, retrieval ‐ augmented generation). Experience with system integration, APIs and data connectivity. Strong stakeholder engagement skills, with the ability to translate technical solutions into ...

markets and infrastructure Desirable attributes: Hands‐on experience building LLM‐based systems Experience testing non‐deterministic systems Understanding of statistics and inferential methods LangGraph, RAG, MCP, MLOps, IaaC, AWS What we offer Private Medical Insurance Dental Insurance Parental Support Salary‐Exchange Pension Employee Assistance Programme (EAP) Local Oxford Discounts Cycle ...

equivalentsPrompt engineering, context design and agentic workflow frameworksEvaluation harnesses, evaluation datasets and automated test suites for AI outputsRetrieval-augmented generation (RAG), vector search, embeddings and retrieval pipelines (desirable)LLM orchestration frameworks (LangChain, Semantic Kernel or equivalents – desirable)Technical and Professional ExpertiseStrong software engineering background … GitHub Copilot, Cursor or equivalents, with a practical view of where they help and where they mislead.Preferred Qualifications and ExperienceRetrieval-augmented generation, agentic workflows, tool use or fine-tuning in production settings.Experience with LLM APIs, orchestration frameworks, vector search, embeddings, retrieval pipelines, evaluation datasets ...

equivalentsPrompt engineering, context design and agentic workflow frameworksEvaluation harnesses, evaluation datasets and automated test suites for AI outputsRetrieval-augmented generation (RAG), vector search, embeddings and retrieval pipelines (desirable)LLM orchestration frameworks (LangChain, Semantic Kernel or equivalents – desirable)Technical and Professional ExpertiseStrong software engineering background … Copilot, Cursor or equivalents, with a practical view of where they help and where they mislead. Preferred Qualifications and ExperienceRetrieval-augmented generation, agentic workflows, tool use or fine-tuning in production settings. Experience with LLM APIs, orchestration frameworks, vector search, embeddings, retrieval pipelines, evaluation ...

rather than hype to determine whether an AI approach is actually working. It would be advantageous if you have experience with: RAG (Retrieval-Augmented Generation) Agentic workflows and tool use Fine-tuning Vector search and embeddings Retrieval pipelines LLM orchestration frameworks such ...

articulate the business problem behind the technology you're building. It would be advantageous if you also have experience with: RAG (Retrieval-Augmented Generation) Agentic workflows and tool use Vector databases/search and embeddings LLM APIs from multiple providers AI evaluation frameworks ...

across a large enterprise. You will drive security architecture, enforce secure-by-design patterns and collaborate with engineering, cloud and security teams on LLMs, RAG, AI agents and data flows. The role is hybrid with bases in London or Reading. Visa sponsorship is available for candidates currently living ...

language model APIs across multiple providersAI coding tools: GitHub Copilot, Cursor or equivalentsPrompt engineering and context design patternsRetrieval-augmented generation (RAG), vector search, embeddings (desirable)Evaluation frameworks and automated quality pipelines for AI outputsTechnical and Professional ExpertiseSolid production experience with C# .NET, including working in established … results to improve quality.Daily fluency with AI coding tools such as GitHub Copilot, Cursor or equivalents.Preferred Qualifications and ExperienceRetrieval-augmented generation, agentic workflows, tool use, vector search or embeddings in production settings.Experience with LLM APIs across more than one provider, with a feel for their trade ...

cloud services (compute, storage, networking, security). Desirable Exposure to applying AI/ML techniques to business problems. Exposure to GenAI, LLMs, RAG or agent-based workflows. Experience using AI-assisted development tooling (e.g. GitHub Copilot, Cursor) to accelerate delivery. Experience working in an agile environment. Experience in financial services … such as Streamlit or ReactJS. Awareness of the AI/ML model lifecycle, training data, evaluation, tuning, monitoring. Awareness of GenAI concepts, prompting, embeddings, RAG, vector databases. Knowledge of Snowflake specifically, and its integration patterns on AWS. Awareness of enterprise architecture, security and regulatory considerations in financial services. Disability Confident ...

language model APIs across multiple providersAI coding tools: GitHub Copilot, Cursor or equivalentsPrompt engineering and context design patternsRetrieval-augmented generation (RAG), vector search, embeddings (desirable)Evaluation frameworks and automated quality pipelines for AI outputsTechnical and Professional ExpertiseSolid production experience with C# .NET, including working in established … improve quality. Daily fluency with AI coding tools such as GitHub Copilot, Cursor or equivalents. Preferred Qualifications and ExperienceRetrieval-augmented generation, agentic workflows, tool use, vector search or embeddings in production settings. Experience with LLM APIs across more than one provider, with a feel for their ...

Solution Delivery Lead the design, development and deployment of AI-integrated applications using modern full-stack technologies. Build features powered by LLMs, agentic workflows, RAG patterns and MCP integrations. Work directly with customers to shape requirements and translate them into working software. Integrate Azure AI services such as Azure OpenAI …/Node.js, .NET/C#, Python/FastAPI). Proven background delivering production software in client-facing environments. Experience with LLM integration, prompt engineering, RAG or agentic AI development. Familiarity with AI-assisted development tools (GitHub Copilot, Claude, Cursor). Hands-on experience with Azure cloud services and CI/ ...

dependency mapping, service impact, and fault propagation. Work with AI/LLM engineers to provide high-quality features, embeddings, metadata, and contextual datasets for RAG and agentic AI systems. Define network data quality rules, correlation logic, and entity resolution methods. Create reusable analytical models for RAN, Core, IP/MPLS … assessment. Experience with graph analytics, entity relationship mapping, or knowledge graph concepts. Understanding of LLMs and how structured data can support AI agents and RAG systems. Experience with BigQuery or similar data warehouse/analytics platforms. Required Technical Skills Python. Statistics and ML basics. Network KPI modelling. RAN, Core ...

organization.Shape our generative-AI direction. Own the strategy for applying LLMs and generative AI across the Experiences product — conversational trip planning, retrieval-augmented generation grounded in our first-party reviews and content, and automated content — with rigorous evaluation to control quality and cost, including ...