The posting
Overview
We are looking for hands-on AI Application Engineers with strong AI literacy to help solve the AI democratisation problem: many teams are building promising AI prototypes with high enthusiasm, but most are not yet ready for production. The answer is not to stop vibe coding or slow down experimentation, but to create a controlled path from prototype to production with clear ownership, prioritisation, engineering hardening and reusable platform patterns.
This role sits within the AI Portfolio & Acceleration Squad in Platform & Software Engineering Division and supports the organisation's move towards governed, scalable and responsible AI adoption. The successful candidate will work across business users, product owners, platform engineers, data teams, cyber/security, privacy and operations stakeholders to assess, rebuild, harden and productise high-value AI use cases at pace. The role requires strong software engineering fundamentals, practical fluency with AI-assisted development tools, and the ability to use AI to scale engineering throughput, shorten delivery cycles and accelerate MVP-to-production conversion while maintaining production discipline, security, compliance, observability and long-term supportability.
Key Responsibilities
- Refactor prototypes and vibe-coded applications into production-grade solutions with clean architecture, maintainable code, secure authentication, robust APIs and automated deployment pipelines.
- Design, build and harden AI-enabled applications, including chatbots, RAG solutions, workflow assistants, agents, automation tools and AI-assisted business applications.
- Work with product owners and business stakeholders to clarify use-case outcomes, user journeys, operational ownership, adoption metrics and production-readiness requirements.
- Implement full-stack application capabilities across frontend, backend, APIs, data integration, authentication, authorization, logging and monitoring.
- Integrate applications with approved AI services such as Azure OpenAI, Azure AI Foundry, Azure AI Search, Azure Machine Learning, Microsoft Graph, enterprise APIs and internal data sources.
- Apply secure and responsible AI application patterns, including prompt management, retrieval grounding, input/output controls, human-in-the-loop design, auditability and content safety controls.
- Develop reusable implementation patterns, starter templates and engineering playbooks for AI application delivery across common use cases.
- Support production-readiness assessments covering security, privacy, data classification, model behaviour, observability, cost, support model and operational handover.
- Build automated test suites for AI applications, including functional tests, regression tests, prompt evaluation, response quality checks and guardrail validation.
- Implement observability for AI applications, including application logs, model usage, latency, token consumption, errors, user feedback, cost and key business metrics.
- Collaborate with platform engineers to deploy AI applications using approved cloud patterns, CI/CD pipelines, containerisation, API management, secrets management and monitoring baselines.
- Document solution designs, operating procedures, reusable patterns, known limitations and support guides to ensure applications are maintainable after go-live.
Required Skills and Experience
- 7+ years of hands-on software engineering experience, including experience building, deploying and supporting enterprise or cloud-native applications.
- Strong full-stack engineering capability using modern frontend, backend and API development frameworks such as React, TypeScript, Node.js, Python, .NET, Java or equivalent technologies.
- Hands-on experience designing and integrating REST APIs, backend services, databases, authentication mechanisms and enterprise application integrations.
- Practical experience building AI-enabled applications using large language models, RAG patterns, prompt engineering, embeddings, vector search, agents, workflow automation or AI orchestration frameworks.
- Working knowledge of Azure AI services such as 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 applying secure software development practices, including input validation, secrets management, least-privilege access, dependency scanning, logging, error handling and secure configuration.
- Experience with modern authentication and authorization standards, including OAuth 2.0, OpenID Connect, SAML, JWT, RBAC and enterprise identity integration using Microsoft Entra ID.
- Hands-on experience with CI/CD pipelines using Azure DevOps, GitHub, GitHub Actions, ShipHATS or equivalent platforms.
- Familiarity with containerisation, cloud deployment patterns, environment promotion, deployment rollback and production support practices.
- Ability to assess prototype quality and determine what must be rebuilt, hardened, monitored or redesigned before production release.
- Good understanding of AI risks, including hallucination, data leakage, prompt injection, unsafe tool use, policy bypass, privacy risks and poor explainability.
- Strong documentation, communication and stakeholder management skills, with the ability to explain technical design choices and production trade-offs clearly.
- Comfortable working in an agile, product-oriented environment where solutions are delivered iteratively and improved through user feedback, platform patterns and governance review.
Preferred Skills
- Experience building chatbots, knowledge assistants, workflow agents, document intelligence solutions, recommendation assistants or AI-enabled internal tools.
- Experience working with AI application frameworks such as LangChain, Semantic Kernel, LlamaIndex, AutoGen, CrewAI or equivalent orchestration tools.
- Experience with vector databases or search technologies such as Azure AI Search, PostgreSQL with pgvector, Cosmos DB, Pinecone or similar platforms.
- Experience with AI evaluation, prompt testing, red teaming, safety evaluations, grounding quality checks or responsible AI controls.
- Experience integrating with Microsoft 365, SharePoint, Teams, Microsoft Graph, Power Platform or enterprise workflow systems.
- Familiarity with public sector cloud environments, government security requirements, data classification, privacy and compliance obligations.
- Exposure to observability, SRE practices, incident response, service health dashboards and production support models.
- Experience using AI-assisted development tools such as GitHub Copilot, Microsoft Copilot, Claude, ChatGPT Enterprise or equivalent tools to improve engineering productivity, testing and documentation.
