Lead AI Engineer - RAG and Cloud Infrastructure

Lead Engineer AI, RAG & Cloud Infrastructure Are you an experienced engineer who combines software engineering, cloud infrastructure and Generative AI? Do you enjoy building production-grade AI solutions while providing technical direction and bringing teams together? For a large international organisation, we are looking for a Lead Engineer to help shape and further develop a modern RAG-based chatbot platform. This is a hands-on technical leadership role for someone who understands both the AI application layer and the underlying infrastructure required to run these solutions reliably at scale. The role You will join an engineering organisation responsible for an enterprise-grade platform that combines document processing, information retrieval and Large Language Models to deliver intelligent chatbot experiences to users. The platform is continuously evolving. While parts of the existing document-processing environment are focused on stability and optimisation, the chatbot platform is actively being improved with a strong focus on quality, performance and new capabilities. As Lead Engineer, you will help define the technical direction and ensure that ideas are translated into robust, scalable and maintainable solutions. The engineering organisation operates through several autonomous workstreams. Following a recent organisational integration, an important part of your role will also be helping establish alignment across teams and creating a consistent engineering approach. What you will do Provide technical leadership across the AI, RAG and cloud platformDesign, develop and improve production-grade RAG and LLM solutionsWork with document processing, embeddings, vector search and information retrievalImprove the quality, accuracy, performance and reliability of chatbot solutionsDesign and maintain scalable cloud infrastructure and platform servicesDevelop APIs, integrations and distributed services using modern engineering practicesDrive best practices around CI/CD, Infrastructure as Code, security and observabilityIdentify architectural and technical improvements and turn them into actionable initiativesWork closely with software engineers, AI specialists, platform engineers and product stakeholdersProvide technical guidance and support to multiple workstreamsHelp create alignment between teams following a recent organisational integrationCommunicate architectural decisions and technical concepts clearly to both technical and non-technical stakeholdersRemain hands-on and contribute directly to the engineering challenges of the platform What we are looking for We are looking for an engineering-first profile rather than a purely managerial or research-oriented AI professional. You bring: 4+ years of experience in software, cloud, platform or infrastructure engineeringStrong hands-on experience with Retrieval-Augmented Generation (RAG)Experience developing applications using LLMs / Generative AIExperience with production-grade AI, chatbot or knowledge-retrieval platformsStrong experience with cloud infrastructure, preferably AzureStrong Python development experienceExperience with APIs, microservices and distributed systemsKnowledge of vector databases, vector search, embeddings and semantic searchExperience with document processing and information retrievalExperience with DevOps, CI/CD and Infrastructure as CodeExperience taking technical ownership or acting as a Lead, Staff or Principal EngineerStrong communication and stakeholder management skillsThe ability to bring structure and alignment to complex environmentsA pragmatic, proactive and delivery-focused mindset Nice to have Experience with one or more of the following is highly beneficial: Azure OpenAIAzure AI SearchDatabricksKubernetesTerraformLangChain or LlamaIndexMLOps / LLMOpsAI/RAG evaluation and quality frameworksAI observability and monitoringEnterprise-scale cloud platformsLarge-scale document processing environments