26 to 47 of 47 Retrieval-Augmented Generation Jobs in the South East

governance position: you make the architectural calls rather than facilitate them. You will: Design large-scale agentic AI architectures: LLM document processing, structured extraction, RAG, invoice-to-contract matching Own low-level design decisions, including API design, data models and service boundaries Set and drive technical processes: engineering standards, security ...

practices within engineering teams Drive improvements in automation frameworks and testing tools Provide expert oversight on AI model validation, including Generative AI and RAG solutions Identify risks early and implement mitigation strategies Mentor and coach engineers to build strong testing capability across teams Key Responsibilities Define and deliver testing strategies … platforms) Proficiency in one or more: Python, Java, JavaScript, SQL, or R Proven experience in: AI/Generative AI testing RAG (Retrieval-Augmented Generation) solution validation (e.g. RAGAS framework) CI/CD, DevOps, and cloud-based test integration Ability to define and implement ...

/CD pipelines (Azure DevOps). * Demonstrated hands-on exposure to at least one of: LLM API integration, vector databases, prompt engineering, or RAG pipeline construction * Familiarity with REST-based AI APIs (OpenAI, Anthropic, Google Vertex AI, or equivalent). * Basic understanding of embeddings, semantic search, and token-based context ...

Extensive Experience: Proven track record of leading the delivery and maintenance of complex software products in a DevOps and Agile environment.Deep practical experience with RAG, LLMs, and MLOps.Expert-level understanding of NLP, Embeddings, and Prompt Engineering.Expert proficiency in Python, React, and TypeScript.Significant experience with Cloud platforms (GCP or Azure ...

production-grade LLM systems with a strong focus on performance, reliability, security, and cost-efficiency Work extensively with unstructured data using RAG (Retrieval-Augmented Generation), alongside structured (SQL) and time-series/streaming data Develop robust APIs and integration layers for LLM capabilities Collaborate ...

learning solutions Practical experience with Large Language Models (LLMs), Generative AI and prompt engineering Knowledge of modern AI tooling and frameworks, including exposure to RAG architectures and vector databases Experience working with cloud platforms, ideally Google Cloud Platform (GCP) Strong software engineering fundamentals and experience developing scalable applications Excellent communication ...

Experience with MCP and Vertex/storage-related infrastructure Strong understanding of AI architecture, orchestration, and scalable deployment practices Preferred Experience Building AI agents, RAG pipelines, or enterprise AI applications Working with cloud-based AI/ML platforms and data storage solutions Collaborating with engineering and product teams to deliver ...

bring a strong STEM/computing background. Knowledge and understanding of UK Defence. Experience in one or more of the following technical disciplines: LLMs, RAG,Agentic AI(e.g. LangGraph). Computer Vision. AI for audio and speech. What we offer We offer a combination of mentoring and internal and external ...

know what it means to balance craft, ownership, and speed Familiarity with tools that power today's AI agents: eval frameworks, agent tooling, RAG pipelines, and prompt engineering Prior experience with React, TypeScript, and/or Go Previous roles where you interfaced with customers or led technical projects with external ...

solutions). Lead architectural decisions , ensuring responsible AI, explain ability, security, and operational robustness are embedded by design. Evaluate and integrate LLMs, vector databases, RAG patterns, agent-based frameworks, and AI APIs into enterprise-ready solutions. Champion automation across the AI lifecycle from data ingestion to deployment and run. Service … cloud platforms (AWS, Azure or GCP) and modern DevOps practices Experience integrating machine learning/GenAI models into real-world systems Experience with LLMs, RAG, vector search, conversational AI, or unstructured data pipelines Familiarity with AI tooling/frameworks (e.g. LangChain, LlamaIndex, Haystack, Hugging Face, CrewAI) Experience leading SaaS/ ...

Robotics team following continued growth and investment. This is an exciting opportunity to join a multidisciplinary engineering team developing next-generation intelligent systems that combine AI, machine learning and robotics to solve complex real-world challenges. Working closely with software engineers, data scientists and product teams … modern software architecture. Experience working within Agile development environments. Excellent communication and stakeholder engagement skills. Desirable Experience with ROS/ROS2. Experience with LLMs, RAG or Agentic AI architectures. Knowledge of reinforcement learning or motion planning. Familiarity with Docker, Kubernetes and CI/CD. MSc or PhD in Computer Science ...

deployment Build robust evaluation harnesses—offline metrics, online experiments, guardrails and monitoring Apply LLMs and generative AI techniques where they're the right tool—RAG, fine-tuning, prompt engineering, agentic patterns Monitor models in production for drift, degradation, bias and safety concerns Partner with data engineering peers to build … experience—deploying, serving and monitoring models at scale LLM and generative AI tooling exposure (LangChain, LlamaIndex, vector databases such as Pinecone, Weaviate or pgvector, RAG patterns, fine-tuning workflows) MLOps platforms (MLflow, Kubeflow, Vertex AI, SageMaker, Databricks or equivalent) Cloud experience (AWS, GCP, Azure), containerisation and basic data engineering/ ...

Technology, Media or Telecoms sectors. Deep understanding of the Generative AI landscape and its commercial applications, with familiarity across technologies such as LLMs, RAG architectures, vector search, prompt design and AI platform operations. Experience overseeing the end-to-end delivery of AI initiatives, working closely with technical specialists to shape ...

service platforms that allow teams to rapidly integrate AI into coding, testing, deployment, monitoring and operations. You'll establish best practices for prompt engineering, RAG architectures, agentic workflows, model versioning, experimentation and governance, ensuring AI capabilities are scalable, secure and production ready. Beyond the technology, you'll play a pivotal … delivering large-scale, developer facing platforms and leading complex technical initiatives You have hands-on experience building AI-enabled applications using LLMs, agentic frameworks, RAG, prompt engineering and modern GenAI tooling You have a strong knowledge of software engineering fundamentals, including system design, APIs, CI/CD, testing, observability, cloud ...

working in regulated environments or with legal workflows. Thorough understanding of AI technologies used in legal environments (LLMs, NLP, extraction/classification models, summarisation, RAG pipelines, etc.) Hybrid Working Birketts is a flexible business which has embraced a hybrid working model where our colleagues enjoy a mix of home ...

Data Science AI Engineer - RAG Chatbot LangGraph exp London - Hybrid. Circa £500 – £675 per day (and negotiable DOE) Contract (Outside IR35) Agentic AI/Machine Learning. Company: Our client is a globally established B2B information and professional services business, operating across multiple high-value industry sectors. They have established data … exploration, modelling, experimentation, and production deployment — while contributing to systems used by global What you'll be working on as Data Science AI Engineer - RAG Chatbot LangGraph exp: AI Agents powered by LLMs and advanced RAG/Agentic architectures. LLM Chatbots that support user’s queries through automated search, content ...

consultative environment. Responsibilities Design end-to-end AI and Generative AI architectures for enterprise-scale transformation programmes Define solution architectures leveraging LLMs, RAG, vector databases and AI agent frameworks Work with senior client stakeholders to translate business challenges into scalable AI solutions and implementation roadmaps Design secure, responsible and scalable … experience designing and delivering enterprise AI, Machine Learning or Advanced Analytics solutions Strong understanding of modern AI technologies including Generative AI, LLMs, Prompt Engineering, RAG and Vector Databases Experience architecting production-grade AI platforms and applications Strong knowledge of at least one major cloud platform (Azure, AWS or GCP) Ability ...

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 ...

Senior AI/ML Engineer (LLM's/RAG Pipeline Development)Guildford, Surrey (Fully Onsite)£85000 - £125,000 + 25% Bonus, 10% Pension, Private Medical.- Must have a Masters or PhD Degree in a STEM/Computing discipline.- Must work full-time, 5 days a week in the Guildford office. ...

party platforms Develop microservices, wrappers, connectors, and service interfaces to support solution components Support applied AI development including LLM services, speech services, classification models, RAG pipelines, and AI-enabled application features Prepare and maintain demo-ready technical builds for internal and customer-facing demonstrations Support the preparation of technical handoff … environment Excellent communication skills to articulate technical issues and blockers clearly Desirable Skills: Experience with AI/ML tools, LLMs, speech services, RAG systems, or AI APIs Experience with Unreal Engine, Unity, or other real-time 3D development environments Familiarity with Docker, FastAPI, REST APIs, Git, and deployment workflows Experience ...

solution concepts into actionable architecture, design and delivery guidance for engineering teams. Design and implement AI-powered assistants, agents and intelligent workflow solutions leveraging RAG and advanced orchestration techniques. Evaluate emerging AI technologies, frameworks and industry trends to drive innovation and best practice. Provide technical leadership, mentoring and guidance … strongly preferred (e.g., Bedrock, Lambda, Step Functions and related AI services). Hands-on experience implementing AI agents, multi-agent systems, intelligent workflow automation, RAG architectures and AI-powered assistants in enterprise environments. Strong knowledge of agentic frameworks and orchestration technologies such as LangGraph, AutoGen, CrewAI, Agent Development ...

platforms built on AWS. Working closely with senior stakeholders, product teams and engineering leads, you'll design and implement AI agents, multi-agent systems, RAG architectures and intelligent workflow solutions leveraging AWS services including Bedrock, Lambda and Step Functions. You'll be responsible for defining architecture standards, shaping technical strategy … remaining hands-on with the latest AI technologies. SC Clearance OR eligibility is madatory. Key Skills: AWS Bedrock, Agentic AI, Generative AI, AI Agents, RAG, LangGraph, CrewAI, AutoGen, ADK, Solution Architecture, AWS Lambda, Step Functions, Insurance, Enterprise Architecture, AI Strategy. ...