AI Foundry Engineer

Job description / Role

Job summary

We are looking for an experienced AI Foundry Engineer to design, develop, and deploy enterprise-grade AI solutions using Python, Microsoft Azure, Azure AI Foundry, and OpenAI technologies. The role is ideal for an AI/ML engineer who can translate business requirements into scalable AI applications and work across the complete AI solution lifecycle, from experimentation and development to deployment and optimisation.

The ideal candidate will have strong hands-on engineering capabilities, a solid understanding of modern generative AI architectures, and practical experience building production-ready solutions within the Microsoft Azure ecosystem.

Requirements

Key responsibilities

• Design, develop, and deploy AI and generative AI solutions using Microsoft Azure.
• Build production-ready AI applications using Azure AI Foundry and OpenAI technologies.
• Develop scalable AI services, APIs, automation workflows, and intelligent applications using Python.
• Design and implement LLM-powered applications, including RAG pipelines, AI agents, copilots, and conversational solutions.
• Integrate Azure OpenAI models and other AI services into enterprise applications.
• Develop prompt engineering strategies and optimise model responses for accuracy, relevance, and reliability.
• Build data and retrieval pipelines to support context-aware AI applications.
• Work with vector databases, embeddings, document processing, and knowledge-retrieval systems where required.
• Evaluate AI models and solutions using appropriate quality, performance, and business metrics.
• Implement security, access controls, monitoring, logging, and governance for AI workloads.
• Optimise AI applications for scalability, latency, reliability, and cloud costs.
• Collaborate with software engineers, data teams, product managers, and business stakeholders to translate requirements into technical solutions.
• Develop technical documentation, architecture diagrams, APIs, and implementation specifications.
• Troubleshoot production issues and continuously improve deployed AI solutions.
• Stay current with developments in Azure AI Foundry, OpenAI, LLMs, generative AI, AI agents, and emerging AI engineering practices.
• Contribute to establishing reusable AI components, development standards, and best practices across projects.

What makes you a great fit

• Five plus years of experience in software engineering, AI/ML engineering, data engineering, or a closely related technical field.
• Strong hands-on programming experience with Python.
• Practical experience with Microsoft Azure and cloud-based application development.
• Strong experience with Azure AI Foundry and/or Azure OpenAI Service.
• Demonstrated experience building and deploying generative AI and LLM-based applications.
• Strong understanding of RAG, embeddings, vector search, prompt engineering, AI agents, and LLM orchestration.
• Experience integrating OpenAI or similar foundation models into production applications.
• Knowledge of APIs, microservices, databases, cloud architecture, and software development best practices.
• Experience with AI application evaluation, monitoring, security, and performance optimisation.
• Ability to convert business requirements into scalable and maintainable technical solutions.
• Strong debugging, analytical, and problem-solving skills.
• Excellent communication and stakeholder-management abilities.
• Comfortable working in a fast-paced environment with evolving AI technologies and requirements.
• Experience with Azure services such as Azure Functions, Azure AI Search, Azure Storage, Azure Kubernetes Service, Azure DevOps, and Microsoft Entra ID is an advantage.
• Familiarity with CI/CD, Docker, Kubernetes, Git, and infrastructure-as-code practices is desirable.
• Relevant Microsoft Azure or AI certifications are an added advantage.