> Markdown version of [/jobs/ext/3330099-senior-ai-software-engineer-azure](https://www.wearedevelopers.com/jobs/ext/3330099-senior-ai-software-engineer-azure). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Senior AI Software Engineer (Azure) - **Company:** Capgemini Sogeti - **Location:** London, UK - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** .NET Framework, Application Programming Interfaces (APIs), Artificial Intelligence, Application Integration Architecture, Microsoft Azure, C Sharp (Programming Language), Python (Programming Language), Azure Machine Learning, Search Technologies, Enterprise Software Applications, Retrieval-Augmented Generation, Delivery Pipeline, Large Language Models, Multi-Agent Systems, Prompt Engineering, Backend, SC Clearance, Build Management, Containerization, Cosmos DB, Machine Learning Operations, Software Version Control, Api Management, Docker, Legacy Systems - **Published:** September 28, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=196c9395632b808d ## About the Role * Production experience building LLM-based applications on Azure that went live and that you then supported, rather than proofs of concept that stopped at demo. * Strong production coding in Python and/or C#/.NET, including building and integrating APIs and backend services. * Practical depth in retrieval-augmented generation: chunking and embedding strategy, retrieval tuning, and evaluating the groundedness and accuracy of outputs in a live system. * Client-facing delivery experience, comfortable with ambiguity and shifting priorities, and able to explain technical trade-offs to people who are not engineers., To obtain SC clearance, the successful applicant must have resided continuously within the United Kingdom for the last 5 years, along with other criteria and requirements. ## Description ou will design, build and ship agentic AI applications on Microsoft Azure for clients in regulated and high-governance sectors. This is a hands-on engineering role in a product-aligned team: you will take a solution from first design through to live production, and then keep it running. We work across Retail, Utilities, Manufacturing, Transport, Health and the Public Sector, so you will pick up new domains quickly and often. * A multi-agent case-handling assistant for a public sector client, retrieving from several legacy systems of record, with full audit trails and human-in-the-loop approval on every outbound decision. * A document-intelligence pipeline for a utilities client that extracts structured data from tens of thousands of scanned engineering records, with automated groundedness and accuracy evaluation gating each release. * An internal developer platform capability that lets a retail client's own engineers deploy evaluated, guardrailed agents against their product data without going through us each time. Your Role Delivery and technical leadership * Act as a trusted technical voice for architects, product owners and client stakeholders, turning business problems into agentic AI solution designs. * Own solutions across the full lifecycle, from design through to production support. * Explain technical trade-offs and AI risk and value clearly to non-technical stakeholders. * Reflect compliance and audit requirements in technical delivery decisions when working in regulated client environments. * Mentor and pair with less experienced colleagues. Engineering * Build and deploy agentic AI applications and multi-agent systems on Azure using Microsoft Foundry (formerly Azure AI Foundry) and the Azure AI Services portfolio, including Azure OpenAI, Azure AI Search and Azure AI Document Intelligence. * Develop production-grade AI-enabled services and APIs in Python and C#/.NET, integrating agents and models with enterprise applications and data sources. * Apply prompt engineering, retrieval-augmented generation and agent orchestration patterns to build reliable, tool-using workflows. * Implement guardrails, content safety, evaluation, monitoring and governance for generative and agentic solutions. * Integrate with Azure-native services (Functions, Container Apps, AKS, API Management) and CI/CD pipelines. * Support LLMOps practices: prompt and model versioning, automated evaluation, deployment pipelines and observability for AI workloads in production., * Breadth across agent orchestration frameworks (Semantic Kernel, LangGraph, AutoGen) so you can make an informed call on which fits a use case rather than defaulting to the one you know. * Judgement on the model landscape: selecting between proprietary and open-weight models on cost, latency and quality, and revisiting that as the landscape shifts. * Multi-agent systems and tool-calling and function-calling patterns. * Containerisation and orchestration for AI workloads at scale (Docker, AKS). * Vector search at scale (Azure AI Search, Cosmos DB vector search). * LLMOps and MLOps tooling and automated evaluation harnesses. * Data privacy, security and compliance for AI systems, including responsible AI standards and GDPR considerations. * Delivery in regulated and high-governance environments. We are a Disability Confident Employer Capgemini is proud to be a Disability Confident Employer (Level 2) under the UK Government's Disability Confident scheme. As part of our commitment to inclusive recruitment, we will offer an interview to all candidates who: * Declare they have a disability, and ## Related Videos - [Inside the AI Revolution: How Microsoft is Empowering the World to Achieve More](https://www.wearedevelopers.com/videos/869-inside-the-ai-revolution-how-microsoft-is-empowering-the-world-to-achieve-more) - [Developer Tools for Microsoft Azure](https://www.wearedevelopers.com/videos/450-developer-tools-for-microsoft-azure) - [Developing the Backend with Stefan Lingler, CTO at Shpock](https://www.wearedevelopers.com/videos/100360-developing-the-backend-with-stefan-lingler-cto-at-shpock) - [Docker Compose: Rediscovered](https://www.wearedevelopers.com/videos/1978-docker-compose-rediscovered) - [Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure](https://www.wearedevelopers.com/videos/1532-agentic-ai-from-theory-to-practice-developing-multi-agent-ai-systems-on-azure) - [Implementing an Event Sourcing strategy on Azure](https://www.wearedevelopers.com/videos/688-implementing-an-event-sourcing-strategy-on-azure) ## Related Articles - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [What Are The Top Skills Required For Azure Developers?](https://www.wearedevelopers.com/magazine/77-what-are-the-top-skills-required-for-azure-developers) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift) - [Dev Digest 137 - AI'm not sure about this](https://www.wearedevelopers.com/magazine/485-dev-digest-137-ai-m-not-sure-about-this) - [The State of WebDev AI 2025 Results: What Can We Learn?](https://www.wearedevelopers.com/magazine/581-the-state-of-webdev-ai-2025-results-what-can-we-learn) - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development)