14 of 14 Contract Retrieval-Augmented Generation Jobs in the UK excluding London

LlamaIndex for building LLM-powered applications Vector Databases: FAISS, Weaviate, Pinecone, Qdrant (Nice-to-Have) Retrieval-Augmented Generation (RAG): Experience building hybrid systems combining LLMs with enterprise data MLOps & Infrastructure MLOps: Model versioning, monitoring, logging Bias Detection & Mitigation Content Filtering & Moderation Explainability & Transparency ...

business requirements into technical architectures for GenAI and machine learning use cases. Implement prompt engineering, retrieval-augmented generation (RAG), and integration patterns with enterprise systems. Configure and optimise Microsoft Copilot Studio and other AI tools for internal use cases. Support the development of repeatable … Azure AI services. Strong ability to quickly prototype and test AI/ML solutions. Experience with APIs, vector databases, and integration patterns. Understanding of RAG, LLMOps, and prompt engineering. Job Offer Competitive daily rate (Inside IR35). Opportunity to work on innovative AI projects in the financial services industry. Temporary ...

. Multi-Agent Ecosystems: Design architectures that support Agent-to-Agent (A2A) communication, orchestration, and collaboration across diverse business functions. LLM Strategy & RAG: Define model selection, fine-tuning strategies, and build Retrieval-Augmented Generation (RAG) pipelines to ensure contextual accuracy and reduced hallucinations. Context ...

subject matter expert, you will mentor a high-performing team, manage cross-functional integrations, and stay at the bleeding edge of AI (RAG, MCP, and SageMaker) to keep our projects ahead of the curve. What You'll Do Architect Decision Systems: Design innovative AI/ML models that … Science & Machine Learning. Cloud Expertise: Intermediate+ proficiency in Amazon SageMaker . Modern AI: Familiarity with Retrieval-Augmented Generation (RAG) and Model Context Protocol (MCP) . Engineering Rigor: Solid understanding of the Software Development Life Cycle (SDLC) . Please let me know if you would ...

experience and API development Experience with data pipelines and vector databases Knowledge of SRE, DevOps, and platform engineering practices Exposure to AI systems, LLMs, RAG, or agent architectures Experience working with UK government or secure environments You'll work alongside expert architects and engineers to deliver complex, high-impact solutions ...

observability). Demonstrated success in leading teams Deep understanding of AI/ML solutions implementation, with emphasis on LLM applications and retrieval-augmented generation. Expertise in modern SDLC and DevOps: CI/CD (e.g., Jenkins/GitLab), infrastructure as code (e.g., Terraform/CloudFormation), automated testing ...

artificial intelligence, and machine learning, with considerable in-depth knowledge in implementing solutions using AWS. Practical cloud-native experience, specifically with AWS. Experience with RAG-based semantic search and LLM inference workflows using OpenAI and Claude models. ...

/Kent preferred Day Rate: £300–£325 per day Key Requirements: Hands-on exposure to Azure AI and Machine Learning Experience with Agentic AI , RAG systems , and GraphRAG At least 10+ years’ experience in .NET Please note: This role cannot offer sponsorship. Applicants must have full rights to live ...

TypeScript-based applications Understanding of semantic/graph data (e.g., RDF triples, SPARQL , Amazon Neptune ) Ability to validate AI-supported features, including LLM/RAG behaviours via Amazon Bedrock Knowledge of performance testing for serverless architectures and WCAG 2.2 AA accessibility Familiarity with GDS Standards and testing in the public ...

solutions spanning data preparation, modelling, APIs, and production integration* Build and optimise ML and LLM-driven services, including prediction models, personalisation, and retrieval-augmented systems* Collaborate with business stakeholders to frame problems, define success metrics, and deliver measurable outcomes* Develop services, APIs, and integrations that embed … solutions into production environments* Hands-on experience with ML frameworks such as PyTorch, TensorFlow, or scikit-learn* Experience working with LLMs, including prompt design, RAG, or fine-tuning* Experience building APIs and integrating AI systems into real products* Solid understanding of data pipelines, feature engineering, and model evaluation* Experience working ...

Agentic AI solutions aligned to real business workflows Build and orchestrate autonomous agents with planning, reasoning, and tool use Develop LLM-driven systems including RAG, Q&A, and enterprise copilots Integrate GenAI into existing platforms, products, and processes Own delivery end-to-end: design through to production Work closely with … Generative AI and LLMs Agentic AI frameworks such as LangGraph, AutoGen, or CrewAI Python with modern AI libraries (LangChain, Hugging Face, PyTorch) Experience building RAG pipelines and knowledge retrieval systems Cloud platforms: Azure, AWS, or GCP Microsoft/Azure (Highly Desirable) Microsoft AI Foundry Azure AI Agent Service ...

that enhance global sales workflows. Build scalable backend services and full-stack applications for internal teams. Architect, implement, and optimize LLM orchestration frameworks and RAG-based solutions. Collaborate with cross-functional teams to define requirements and deliver innovative tools. Ensure reliability, scalability, and performance of distributed systems handling massive datasets. … workflows . Strong proficiency in Angular (primary frontend); React optional. Hands-on experience with LangChain, LangGraph, and Indexify , with a deep understanding of RAG architectures . Expert-level SQL and experience with BigQuery and vector databases (Pinecone, Weaviate, Vertex AI Search). Proven track record in MLOps and deploying ...

months IR35: Outside Location: London (onsite once per month ) Start: ASAP What you’ll work on Building Agentic AI workflows and automation Designing RAG pipelines for insurance data Developing LLM-powered tools using Python , LangChain , LlamaIndex , and vector databases Evaluating, fine-tuning, and integrating LLMs (OpenAI/Anthropic/Mistral … Data Science & Engineering teams to productionise models What you’ll need Strong Data Science + AI Engineering background Hands-on experience with Agentic AI , RAG , LLMs , LangChain , Python Knowledge of vector search, embeddings, and scalable pipelines Experience working in enterprise or regulated environments Must have insurance domain experience Insurance domain ...

depth knowledge in implementing solutions using AWS. Deep understanding of AI/ML solutions implementation, with emphasis on LLM applications and retrieval-augmented generation. Practical cloud-native experience, specifically with AWS (compute, storage, networking, IAM, KMS, observability). Experience with RAG-based semantic search ...