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

About the Role

We are looking for a hands-on AI Application Engineer with strong full-stack engineering fundamentals and practical experience building AI-enabled applications.

You will work on taking AI prototypes and early-stage MVPs through to secure, scalable and production-ready applications. This includes refactoring prototype or AI-assisted code, building full-stack application capabilities, integrating enterprise AI services, and implementing the security, testing, observability and deployment practices required for production environments.

The role is suited for an engineer who is comfortable moving between rapid AI experimentation and disciplined production engineering, and who can work closely with product, platform, data, security and business stakeholders.

Key Responsibilities

Refactor prototypes and AI-assisted applications into production-grade solutions with clean architecture, maintainable code and robust APIs.

Design, develop and productionise AI-enabled applications such as chatbots, RAG solutions, knowledge assistants, workflow agents, automation tools and other AI-powered business applications.

Develop full-stack capabilities across frontend applications, backend services, APIs, databases and enterprise integrations.

Integrate applications with AI and cloud services such as Azure OpenAI, Azure AI Foundry, Azure AI Search, Azure Machine Learning and other enterprise APIs and data sources.

Implement authentication and authorisation using enterprise identity services and standards such as Microsoft Entra ID, OAuth 2.0, OpenID Connect, JWT and RBAC.

Apply responsible AI engineering practices including retrieval grounding, prompt management, input/output controls, human-in-the-loop workflows, auditability and content safety.

Assess existing prototypes and determine the engineering, security and architectural changes required before production deployment.

Build automated testing covering functional and regression testing, prompt evaluation, response quality, grounding and AI guardrails.

Implement application and AI observability covering logs, errors, latency, model usage, token consumption, costs, user feedback and relevant business metrics.

Develop and maintain CI/CD pipelines and support containerised/cloud-based application deployments.

Apply secure software development practices including input validation, secrets management, least-privilege access, dependency management and secure configuration.

Develop reusable AI application patterns, starter templates and engineering practices to accelerate future AI application delivery.

Support production-readiness reviews covering security, privacy, data classification, model behaviour, monitoring, cost and operational support.

Produce solution designs, technical documentation, operating procedures and support guides for deployed applications.

Collaborate with product owners, business stakeholders, platform engineers, data teams and security teams throughout the application lifecycle.

Requirements

7+ years of hands-on software engineering experience, including building, deploying and supporting enterprise or cloud-native applications.

Strong full-stack development experience using modern technologies such as React, TypeScript, Node.js, Python,.NET and/or Java.

Strong experience developing REST APIs, backend services, databases and enterprise system integrations.

Practical experience developing AI/GenAI applications using technologies and patterns such as:

Large Language Models (LLMs)

Retrieval-Augmented Generation (RAG)

Prompt engineering

Embeddings and vector search

AI agents and workflow automation

AI orchestration frameworks

Experience with Azure services, ideally including Azure OpenAI, Azure AI Foundry, Azure AI Search, Azure Machine Learning, Azure App Service, Azure Container Apps, API Management, Key Vault, Azure Monitor and Log Analytics.

Experience with enterprise authentication and authorisation including OAuth 2.0, OpenID Connect, SAML, JWT, RBAC and Microsoft Entra ID.

Experience implementing CI/CD pipelines using Azure DevOps, GitHub Actions, ShipHATS or similar platforms.

Familiarity with Docker/containerisation, cloud deployment patterns, environment promotion, rollback and production support.

Strong understanding of secure development practices including secrets management, input validation, dependency scanning, logging, error handling and least-privilege access.

Understanding of key AI application risks including hallucination, prompt injection, data leakage, unsafe tool use, privacy risks and policy bypass.

Experience using AI-assisted development tools such as GitHub Copilot, Claude, ChatGPT Enterprise, Microsoft Copilot or equivalent tools.

Strong communication and documentation skills with the ability to work effectively across technical and non-technical stakeholders.

Comfortable working in an Agile, product-oriented engineering environment.

Good to Have

Experience with AI application frameworks such as LangChain, Semantic Kernel, LlamaIndex, AutoGen, CrewAI or equivalent.

Experience with vector search/databases such as Azure AI Search, PostgreSQL/pgvector, Cosmos DB or Pinecone.

Experience building chatbots, knowledge assistants, document intelligence solutions, workflow agents or AI-enabled internal applications.

Experience with AI evaluation, prompt testing, red teaming, safety evaluation, grounding quality assessment and responsible AI controls.

Experience integrating with Microsoft 365, SharePoint, Teams, Microsoft Graph or Power Platform.

Exposure to observability, SRE practices, incident response, service health monitoring and production support.

Experience working within public sector, government or other highly regulated environments.