AI Application Engineer (Full Stack / GenAI / Azure) (1 Year Contract)

About the role

We are seeking a hands‑on AI Application Engineer to transform AI prototypes and early‑stage MVPs into secure, scalable, production‑ready applications. The role blends rapid AI experimentation with disciplined full‑stack engineering, collaborating closely with product, platform, data, security and business teams.

Key responsibilities

• Refactor prototype and AI‑assisted code into clean, maintainable, production‑grade solutions with robust APIs.
• Design, develop and productionise AI‑enabled applications such as chatbots, RAG solutions, knowledge assistants and automation tools.
• Build full‑stack capabilities across frontend, backend, APIs, databases and enterprise integrations.
• Integrate applications with Azure OpenAI, Azure AI Foundry, Azure AI Search, Azure Machine Learning and other enterprise services.
• Implement authentication and authorisation using Microsoft Entra ID, OAuth 2.0, OpenID Connect, JWT and RBAC.
• Apply responsible AI practices including prompt management, retrieval grounding, human‑in‑the‑loop workflows and content safety.
• Develop automated functional, regression and AI‑specific tests and establish observability for logs, latency, model usage and costs.
• Maintain CI/CD pipelines, support containerised/cloud deployments and enforce secure software development standards.

Required profile

• Strong full‑stack engineering fundamentals with experience delivering production‑grade software.
• Comfortable moving between rapid AI prototyping and disciplined production engineering.
• Ability to work closely with cross‑functional stakeholders (product, platform, data, security, business).
• Experience refactoring prototypes, implementing security, testing and observability for AI applications.

Required skills

• Full‑stack development (frontend, backend, APIs, databases, enterprise integrations)
• Azure OpenAI, Azure AI Foundry, Azure AI Search, Azure Machine Learning
• Microsoft Entra ID, OAuth 2.0, OpenID Connect, JWT, RBAC
• CI/CD pipelines, containerised/cloud deployments
• Secure software development practices (input validation, secrets management, least‑privilege access, dependency management, secure configuration)
• Automated testing (functional, regression, prompt evaluation, AI guardrails)
• Observability (logs, errors, latency, model usage, token consumption, cost monitoring)
• Responsible AI engineering (retrieval grounding, prompt management, human‑in‑the‑loop, auditability, content safety)