51 to 75 of 153 Retrieval-Augmented Generation Jobs in London

technical delivery — from requirements gathering through to deployment and ongoing support Hands-on experience with AI/LLM integration (OpenAI, Azure OpenAI), RAG pipelines, or agentic frameworks is a key requirement Will provide technical leadership and mentoring to junior engineers and actively participate in architecture discussions and code reviews Must ...

outcomes. The Role and Deliverables Design, build, and maintain production-grade AI-enabled applications consuming standardised GenAI services such as LLM-based capabilities, RAG, summarisation, and classification. Develop cloud-native microservice or full-stack applications using API-led architectures. Integrate AI capabilities securely and reliably, in line with platform standards ...

production environments — not just prototypes. Key experience required: • Python and production-grade coding • LLMs, AI Agents & Agentic Workflows • LangChain/LangGraph or similar frameworks • RAG Systems • MCP/FastMCP/FastAPI architectures • Cloud platforms (AWS, Azure, or GCP) • AI system deployment, orchestration & optimisation. This role offers the opportunity to work ...

Architect Professional* Databricks Certifications* CDMP Certification* Terraform, Bicep or Infrastructure-as-Code experience* dbt, Airflow or modern orchestration frameworks* Experience supporting AI, GenAI or RAG-based architectures* Experience within Financial Services, Healthcare, Life Sciences, Energy, Retail or Manufacturing Robert Half Ltd acts as an employment business for temporary positions ...

premises, cloud, and hybrid AI solutions. GenAI Leadership: Deploy and customize a variety of generative models, leveraging Azure OpenAI, Vector Databases, and RAG patterns. Technical Governance: Managed and governed technical teams to ensure best practices in AI data engineering. Stakeholder Management: Act as the primary technical point of contact, gaining ...

designing and optimising multi-agent systems for reliability and production performance Understanding of prompt engineering techniques including few-shot learning, chain-of-thought and RAG Familiarity with LLM evaluation strategies and how to measure whether your system is actually working Hands-on with AI orchestration frameworks: LangGraph, LangChain, DSPy ...

Engineering community. What youll bring: A strong understanding of AI, machine learning and agent-based AI concepts, including Retrieval Augmented Generation (RAG), multi-agent systems and conversational agents. Experience developing AI solutions using programming languages such as Python, or similar languages used ...

platforms such as AWS, GCP, or Azure. What you’ll bring Deep, hands-on experience building and deploying production-grade AI systems using LLMs, RAG pipelines, MCPs, and agentic workflows Proven track record of leading complex, client-facing engagements with a forward-deployed mindset, partnering with both technical and business ...

tools, and cloud platforms such as AWS, GCP, or Azure. What you’ll bring: Proven hands-on experience building production-grade solutions using LLMs, RAG pipelines, MCPs, and agentic workflows A forward-deployed, client-first mindset, with experience working directly with both technical teams and business stakeholders Strong delivery capabilities ...

Role 2: Applied AI Engineer Strong backend engineering experience (Python preferred) Deep knowledge of CI/CD, Docker, Kubernetes, and Git workflows Experience building RAG pipelines and AI agent orchestration systems Minimum 5 years of experience 📩 Interested? Message me here or email mmatysik@trg-uk.com ...

fundamentals are there Solid Kubernetes experience (around 80% of the role), with some serverless on top Hands-on experience with LLM-based applications — RAG, vector databases, agent frameworks Product-minded and commercially aware — this isn't a pure SRE or ops profile Comfortable working across Data Science, Engineering, Product ...

agentic AI architectures, with experience integrating AI securely and at scale Practical experience in enterprise AI governance, prompt engineering, and deployment approaches (including RAG, fine-tuning considerations, and risk mitigation) Experience leveraging AI-assisted development tools (e.g. GitHub Copilot, Claude Code) to materially improve engineering productivity and delivery outcomes ...

agentic AI architectures, with experience integrating AI securely and at scale Practical experience in enterprise AI governance, prompt engineering, and deployment approaches (including RAG, fine-tuning considerations, and risk mitigation) Experience leveraging AI-assisted development tools (e.g. GitHub Copilot, Claude Code) to materially improve engineering productivity and delivery outcomes ...

prototypes, products and production ready solutions Designing and implementing end to end AI solutions that integrate with enterprise systems Working with LLMs, prompt engineering, RAG patterns, embeddings and fine tuning Developing AI agents and agentic workflows using modern frameworks Working with vector databases, APIs and modern data platforms Supporting … collaborative, high performing environment Experience Required: Strong Python and SQL experience Applied AI engineering, ML engineering or software engineering background Experience with LLMs, RAG, embeddings, prompt engineering or fine tuning Exposure to LangChain, LangGraph, Agent Development Kit or similar agent frameworks Experience with vector databases such as Pinecone, Chroma ...

Azure AI, GenAI and Agents. Experience with digital assistant solutions enhanced by AI such as Microsoft Copilot. Demonstrable experience with Retrieval-Augmented Generation. Solid understanding of MLOps. Ability to engage confidently with clients and present technical solutions clearly. It would be great if you had: Experience ...

comfortable with backend architecture and API design Hands-on experience with LLMs and agent frameworks, in production or serious personal projects Solid understanding of RAG, vector stores, prompt engineering, and context management Experience with data pipelines and handling both structured and unstructured data CS, data, or software background, formal ...

they’re looking for: Strong experience with Python in a production environment Hands-on experience with LLMs or applied AI (prompt engineering, fine-tuning, RAG, etc.) Experience building APIs and backend services Solid understanding of cloud platforms Ability to work in a fast-paced, product-driven environment Why join? Work ...

shipping reliable systems used by real customers. Key responsibilities Build and deploy LLM-powered features across drafting, prosecution, and litigation workflows Design and maintain RAG pipelines over large, complex legal and technical corpora Own systems from prototype through to production Focus on robustness, evaluation, and reliability in precision-critical ...

deployment and monitoring. Lead end to end delivery of AI and LLM based solutions across underwriting and insurance journeys Build and deploy agentic workflows, RAG pipelines, and LLM powered applications for internal and customer facing products Work across structured and unstructured data, collaborating closely with Machine Learning and GenAI specialists ...

They’re Looking For Proven experience designing & deploying AI/ML solutions Expert knowledge of LLMs, AI frameworks & agent-based systems Experience in building RAG Systems Cloud expertise across AWS/Azure/GCP Ability to turn complex problems into scalable architectures Passion for AI innovation (this ...

performance and compliance standards. Discover the responsibilities Define standardised evaluation rubrics and scoring systems for system performance and safety across various AI archetypes including RAG and agentic workflows Design comprehensive test cases covering deterministic logic and adversarial scenarios to stress test AI outputs Implement automated evaluators such ...

real-world systems. What you'll work on: Integrating AI components (including LLMs) into production applications and workflows Designing and implementing RAG (Retrieval-Augmented Generation) systems Evaluating LLM behavior, identifying failure modes, and implementing mitigation strategies Testing and debugging non-deterministic AI systems …/CD, IaC, testing, containers) Practical experience with AI systems, including LLM behavior and architectures Evaluation techniques and failure mode analysis Experience with RAG and applied AI system design Strong understanding of AI limitations and appropriate use cases Excellent communication and stakeholder engagement skills Eligibility for UK SC-level security ...

Requirements Proven experience leading Data Science, Machine Learning or GenAI initiatives within complex organisations Experience building and deploying LLMpowered applications Strong knowledge of RAG, embeddings, vector databases and retrieval architectures Experience with Azure, Databricks and modern cloudbased AI platforms Track record delivering AI solutions into production environments Experience ...

Requirements AWS Bedrock Expert: Hands-on experience with Bedrock Agents, Knowledge Bases, and model lifecycle management. AI/ML Depth: Strong grasp of FMs, RAG, tool-use, and the failure modes of agentic workflows. Security & Compliance: Deep knowledge of NIST AI RMF, OWASP LLM Top 10, and UK/ ...

Requirements AWS Bedrock Expert: Hands-on experience with Bedrock Agents, Knowledge Bases, and model lifecycle management. AI/ML Depth: Strong grasp of FMs, RAG, tool-use, and the failure modes of agentic workflows. Security & Compliance: Deep knowledge of NIST AI RMF, OWASP LLM Top 10, and UK/ ...