526 to 550 of 876 Retrieval-Augmented Generation Jobs in the UK

outcomes. Even better... Experience building or deploying AI/LLM agents in production hands-on with the tools behind them (eval frameworks, agent tooling, RAG, prompt engineering) working closely with technical counterparts. You've been a founder, founding team member, or operator you know how to balance craft, ownership ...

only custom-building where neither can deliver the required outcome. Support AI-enabled use cases across areas such as board reporting and narrative generation, management reporting summaries, finance process automation, forecasting and planning support, document ingestion and extraction, reconciliation and workflow automation, insight generation from structured … Have: Significant experience in applied AI, machine learning, data science, analytics engineering, automation or AI-enabled transformation. Strong understanding of generative AI, LLMs, RAG, agents, workflow automation, prompt engineering, evaluation and AI solution design. Familiarity with platforms such as Azure OpenAI, Microsoft Fabric, AWS Bedrock, GCP Vertex AI, Snowflake Cortex ...

work. Secure AI Application and Cloud‐AI Guardrails: Define secure design patterns for AI‐enabled applications, including LLM‐based features, retrieval‐augmented generation, AI agents, AI APIs, copilots, and automation workflows. Establish cloud security requirements for AI workloads, including identity, secrets, data storage, network … Risk Management Framework, NIST Generative AI Profile, OWASP Top 10 for LLM Applications, or Cloud Security Alliance AI security guidance. (Desirable) Experience with RAG architecture, AI agents, vector databases, AI APIs, prompt engineering, or AI application threat modelling. (Desirable) Experience building security knowledge assistants, prompt libraries, AI‐assisted review workflows ...

squad's needs evolve. Requirements: Engineering experience: 3+ years in software engineering, with hands-on experience building LLM-powered applications in production (RAG, tool-augmented agents, or agentic workflows). Education: BS in Engineering, Computer Science, or equivalent. Ways of working: Comfortable working autonomously within a defined problem … doesn't make sense, and delivering in short, time-boxed cycles where validated outcomes matter more than perfect solutions. Agentic AI/LLMs: Building RAG pipelines, tool-augmented agents, and agentic workflows; familiar with prompt engineering, context management, evaluation, and observability. Agent fundamentals: Understands how agents use memory ...

production code while guiding technical direction Deep hands‐on expertise building enterprise AI applications using large language models, AI agents, retrieval‐augmented generation, prompt engineering, orchestration frameworks, evaluation methods, and model optimisation techniques Proven ability to take complex AI solutions from prototype to production … platform capabilities that support real‐time and batch AI workloads at enterprise scale Implement advanced large language model applications using retrieval‐augmented generation, prompt orchestration, evaluation frameworks, model optimisation, agentic workflows, and tool integration Make key technical decisions while remaining accountable for practical implementation ...

Inside IR35 Our client, a leading pharmaceutical organisation is looking for an experienced Agentic AI Software Engineer to join a team developing next generation AI platforms, cloud native infrastructure, and intelligent agent based applications that support cutting edge scientific research. Key Skills & Experience Strong Python development experience FastAPI … DevOps practices Production support, monitoring, observability, and incident management Experience with AI/ML frameworks such as PyTorch, TensorFlow, or JAX Exposure to LLMs, RAG, Agentic AI, model serving, or MLOps environments What's on Offer? Work on innovative AI and Agentic AI solutions Hybrid working from London 12-month ...

DevOps best practices. Collaborate with architects, product teams, and engineers to deliver high-quality solutions. Contribute to AI-enabled application development, including LLM and RAG integrations where applicable. Required Skills 10+ years of software engineering experience. Strong hands-on expertise in Java and/or Python. Kubernetes, Docker, Microservices … REST APIs. CI/CD, DevOps, and Agile delivery practices. Preferred Skills Experience with LLM integration, RAG, AI orchestration, or Agentic AI frameworks. Exposure to AI platforms such as Azure OpenAI, OpenAI, LangChain, LangGraph, or Semantic Kernel. Candidate Profile Strong engineering and problem-solving skills. Product engineering mindset with ...

SDET Engineer or Senior DeveloperHas breadth of experience across different tech-stacks, such as JavaScript/TypeScript, Java, C#, or Python, amongst othersExperienced in RAG Weaviate, OpenAI, Agents, MCP, Langchain, Prompt Engineering, Browser-Use, and DjangoExperienced building AI Tools, Agents and Agentic workflows (LangGraph, CrwAI)Hands-on Product building experience … that cuts across the full SDLC - not just test automation and QE.Experienced in building RAG system with a nice-to-have on fine-tuning LLMsCleaning/augmenting dataComfortable with IAS (Infra As Code) eg. giving a high-level specFully understands test automation (across platforms and functional/non-functional ...

efficiency ; shorter cycle times, less manual effort, higher accuracy, lower cost-to-serve. Engineer the agent core: apply prompt engineering, context engineering, prompt caching, RAG/context-graph retrieval, memory, tool/function calling, MCP integration and multi-agent orchestration. Integrate to standards: connect agents into client ecosystems … Agents SDK, AWS Bedrock AgentCore or Microsoft Agent Framework/Semantic Kernel). Solid command of agent engineering: prompt engineering, context engineering, prompt caching, RAG/context graphs, tool/function calling, MCP, and multi-agent orchestration. Eval-driven development: designing evaluation harnesses and measuring agent quality, safety and reliability. ...

efficiency ; shorter cycle times, less manual effort, higher accuracy, lower cost-to-serve. Engineer the agent core: apply prompt engineering, context engineering, prompt caching, RAG/context-graph retrieval, memory, tool/function calling, MCP integration and multi-agent orchestration. Integrate to standards: connect agents into client ecosystems … Agents SDK, AWS Bedrock AgentCore or Microsoft Agent Framework/Semantic Kernel). Solid command of agent engineering: prompt engineering, context engineering, prompt caching, RAG/context graphs, tool/function calling, MCP, and multi-agent orchestration. Eval-driven development: designing evaluation harnesses and measuring agent quality, safety and reliability. ...

Viridien ( www.viridiengroup.com ) is an advanced technology, digital and Earth data company that pushes the boundaries of science for a more prosperous and sustainable future. With our ingenuity, drive and deep curiosity we discover new insights ...

working with technologies including Azure Databricks, Azure Machine Learning, Azure AI Foundry, LangChain, LangGraph and Python, building enterprise AI applications using RAG, vector databases, prompt orchestration and tool‐calling patterns. You’ll need experience with: Deploying LLMs and machine learning models into Azure enterprise environments. Azure Databricks, Azure Machine Learning … ideally Azure AI Foundry. Building production AI applications using LangChain, LangGraph and Python. MLOps/LLMOps including deployment, monitoring, governance and lifecycle management. RAG, vector databases, prompt engineering and tool‐calling patterns. Building end-to-end AI/ML pipelines from data preparation through to production. Working with technical ...

extend platform components-APIs, tooling, and bespoke logic Architecture & Standards: Architect robust, scalable, and compliant Agentic AI solutions across industries Lead multi-agent orchestration, RAG pipelines, and LLM/SLM integration design Champion observability, telemetry, and auditable AI standards Build and maintain reusable frameworks and asset libraries Team & Product: Help …/Vue, SQL, REST/GraphQL DevOps proficiency: Docker, Kubernetes, CI/CD, and major cloud platforms Expertise in LLMs, Prompt Engineering, Vector DBs, RAG pipelines, and Agentic orchestration frameworks Agentic/Integrations: MCP, Salesforce/SAP/Other Excellent communication with both technical and executive stakeholders Mentorship capability ...

audit-ready evidence generation. AI Enablement Implement AI/ML components within the model workflow, including LLM-based automation for model documentation generation and updating, intelligent data quality checks, and workflow assistance. Integrate AI tooling into a controlled, auditable, production-grade environment, with appropriate testing, monitoring, and governance … Solid AI/ML knowledge, including practical experience with machine learning libraries and/or LLM-based application development (e.g., API integration, prompt engineering, RAG-style document workflows). Strong experience with test automation, CI/CD, and modern software engineering practices (Git, code review, containerization). Experience working with ...

build what’s next - together! Role Overview We're hiring a Principal AI Architect to design and architect next-generation AI solutions that transform how enterprises plan and make decisions. You'll lead the architecture for GenAI and Agentic AI systems at Anaplan, working at the intersection … concepts into clear insights for diverse engineering and business stakeholders. Knowledge of Model Context Protocol (MCP) and agent communication standards Experience with vector databases, RAG architectures, and semantic search systems Familiarity with cloud platforms (AWS, Azure, GCP) and their AI services Experience in SaaS or enterprise software companies Our Commitment ...

hackajob is partnering directly with Accenture to hire for this role. Role Description We are building the next generation of AI-native engineering talent engineers who use AI as a core part of how they work, not as an add-on. As an AI Engineer (Software), you will … improve AI-generated outputs; understanding of AI limitations and responsible use Familiarity with agentic system concepts awareness of orchestration frameworks (LangChain,LangGraph, or equivalent), RAG pipelines, and how full-stack applications connect to agent-basedarchitecture; production experience preferred, conceptual understandingrequired #LI-MP About Accenture Accenture is a leading global professional ...

early, and drive progress without being pushedConsulting or client-facing delivery experience is a strong advantageExposure to GenAI applications in decisioning — personalised content generation, AI-driven offer selectionPreferredExperience evaluating purpose-built decisioning solutions and contributing to capex/opex business casesFamiliarity with real-time streaming technologies … Required — Technical SkillsAdvanced Python — writing clean, production-grade code, not just scripts (OOP, async, packaging, testing)Generative AI & LLM development — prompt engineering, fine-tuning, RAG pipelines, context window managementAgentic AI frameworks — LangChain, LangGraph, AutoGen, or similar; building multi-step autonomous workflowsMachine Learning — model development, training, evaluation, and deploymentAPIs & backend development ...

/GCP, contributing production-ready code as part of a delivery team. Build and evaluate AI/LLM solutions, including prompt/RAG patterns and agentic workflows, alongside classical ML where appropriate. Apply ML techniques to forecasting, segmentation/CLV, causal inference, and other business problems. Analyse large, heterogeneous datasets … input to risk, privacy, and controls assessments. Required qualifications, capabilities and skills Familiarity with AI/LLM development patterns and frameworks, including prompt engineering, RAG, LangChain/LangGraph and/or Google ADK. Strong Python and SQL; able to write clean, production-ready code. Strong AI/ML fundamentals, including ...

/GCP, contributing production-ready code as part of a delivery team. Build and evaluate AI/LLM solutions, including prompt/RAG patterns and agentic workflows, alongside classical ML where appropriate. Apply ML techniques to forecasting, segmentation/CLV, causal inference, and other business problems. Analyse large, heterogeneous datasets … technical input to risk, privacy, and controls assessments. Required qualifications, capabilities and skillsFamiliarity with AI/LLM development patterns and frameworks, including prompt engineering, RAG, LangChain/LangGraph and/or Google ADK.Strong Python and SQL; able to write clean, production-ready code. Strong AI/ML fundamentals, including statistics ...

powered applications. Own end-to-end engineering lifecycle: architecture, build, deployment, and optimisation of AI services. Drive adoption of modern AI patterns including RAG, agent orchestration, and event-driven workflows. Ensure production readiness through observability, resilience engineering, and cost optimisation. Agentic AI & OrchestrationOversee development of multi-agent systems using frameworks … Azure OpenAI, AI Foundry, Cognitive Services).Proven expertise in building and scaling distributed, cloud-native systems (AKS, microservices, APIs).Experience with LLM application design: RAG, prompt engineering, orchestration frameworks. Proficiency in modern programming and automation (Python, PowerShell, REST APIs, IaC).Understanding of data platforms (CosmosDB, SQL, Redis) and event-driven ...

based development when needed, particularly during critical delivery phases or proof‐of‐concept work. Support the design and delivery of Generative AI solutions, including RAG architectures, prompt engineering, and integration with Azure AI services (e.g., Azure OpenAI, Azure AI Search). Ensure robust MLOps practices are followed, including model versioning … experiment tracking and model management, and Spark-based data processing. Familiarity with Generative AI concepts and tooling, including working with LLMs, prompt engineering, RAG patterns, and vector search. A solid understanding of MLOps principles, including CI/CD for models, automated testing, and monitoring of deployed solutions. Cloud platform experience ...

/response logging, and safe rollout patterns Preferred Qualifications, Capabilities, and Skills Experience developing generative AI applications, AI agents, vector search, and retrieval-augmented generation patterns Experience building AI agents using frameworks such as LangChain, CrewAI, LangGraph, or similar orchestration platforms Experience operating … integrating serving platforms such as KServe, Ray Serve, NVIDIA Triton Inference Server, Text Generation Inference (TGI), alongside vLLM/llm-d Familiarity with Amazon SageMaker JumpStart, SageMaker Endpoints, and Amazon Bedrock for managed model hosting Experience with online LLM quality monitoring (e.g., hallucination, toxicity, drift detection) and tracing ...

/response logging, and safe rollout patterns Preferred Qualifications, Capabilities, and Skills Experience developing generative AI applications, AI agents, vector search, and retrieval-augmented generation patterns Experience building AI agents using frameworks such as LangChain, CrewAI, LangGraph, or similar orchestration platforms Experience operating … integrating serving platforms such as KServe, Ray Serve, NVIDIA Triton Inference Server, Text Generation Inference (TGI), alongside vLLM/llm-d Familiarity with Amazon SageMaker JumpStart, SageMaker Endpoints, and Amazon Bedrock for managed model hosting Experience with online LLM quality monitoring (e.g., hallucination, toxicity, drift detection) and tracing ...

/response logging, and safe rollout patterns Preferred Qualifications, Capabilities, and Skills Experience developing generative AI applications, AI agents, vector search, and retrieval-augmented generation patterns Experience building AI agents using frameworks such as LangChain, CrewAI, LangGraph, or similar orchestration platforms Experience operating … integrating serving platforms such as KServe, Ray Serve, NVIDIA Triton Inference Server, Text Generation Inference (TGI), alongside vLLM/llm-d Familiarity with Amazon SageMaker JumpStart, SageMaker Endpoints, and Amazon Bedrock for managed model hosting Experience with online LLM quality monitoring (e.g., hallucination, toxicity, drift detection) and tracing ...

vLLM and llm-d (or directly equivalent model serving stacks) in production Experience developing generative AI applications, AI agents, vector search, and retrieval-augmented generation patterns Experience building AI agents using orchestration frameworks such as LangChain, LangGraph, CrewAI, or similar platforms Experience operating ...