Azure AI Engineer

Responsibilities:

AI Solution Implementation

• Solution Build: Implement AI solutions on Azure AI Foundry — including agent design, model selection, prompt flows, evaluation pipelines, and deployment of base and fine-tuned models.

• Generative AI & RAG: Build retrieval-augmented generation (RAG) pipelines using Azure AI Search, Azure OpenAI, and vector stores; consume curated data from upstream data platforms.

• Model Deployment: Deploy models and AI endpoints to Azure Machine Learning, Azure AI Foundry, and Azure Container Apps; manage endpoint scaling, versioning, and traffic routing.

• Integration: Integrate AI services with downstream applications via REST APIs, Azure API Management, and Function Apps.

AI Guardrails & Responsible AI

• Guardrails Implementation: Implement input/output guardrails using Azure AI Content Safety, Prompt Shields, and groundedness checks; configure jailbreak, PII, and harmful-content filters.

• Evaluation: Build evaluation pipelines for safety, groundedness, relevance, and bias using Azure AI Foundry evaluations; embed Responsible AI checks into the deployment workflow.

• Security Awareness: Work within enterprise security patterns — Managed Identity, Key Vault, private endpoints, and RBAC — for all AI services.

Deployment & MLOps

• CI/CD for AI: Build and maintain CI/CD pipelines (Azure DevOps or GitHub Actions) for prompt flows, model evaluation, and endpoint deployment; implement model registry and promotion gates.

• Observability: Instrument AI workloads with Azure Monitor, Application Insights, and Log Analytics; set up dashboards for token usage, latency, cost, and guardrail violations.

• Infrastructure as Code: Contribute to Terraform or Bicep modules for AI Foundry, AML, and AI Search resources (working alongside platform engineering for foundational infra).

Requirements

• Azure AI Stack: Hands-on experience with Azure AI Foundry, Azure OpenAI, Azure AI Search, and Azure AI Content Safety.

• GenAI Engineering: Experience building RAG, agentic, or prompt-flow solutions; familiarity with frameworks such as LangChain, Semantic Kernel, or LlamaIndex.

• Programming: Strong Python skills; comfortable with REST APIs, async patterns, and SDK-based integrations (Azure SDK, OpenAI SDK).

• Data Awareness: Working familiarity with Azure Data Lake Storage Gen2 and Delta tables — sufficient to consume curated data for AI use cases (deep Databricks/PySpark engineering not required).

• DevOps: Hands-on with Azure DevOps or GitHub Actions for CI/CD; Git-based workflows.

• Infrastructure as Code: Comfortable contributing to existing Terraform or Bicep modules.

• Containers & APIs: Working knowledge of Docker and Azure Container Apps for deploying AI services.

• Observability: Azure Monitor, Application Insights, and Log Analytics for AI workload telemetry.

• Guardrails: Practical experience implementing content safety, prompt shields, or groundedness checks in production AI systems.

• Evaluation: Familiarity with offline and online evaluation methods for LLM applications (groundedness, relevance, safety).

• Responsible AI Awareness: Understanding of Responsible AI principles and regional compliance considerations relevant to UAE / regulated industries.

• Collaboration: Works closely with architects, data engineers, and security teams; communicates clearly across technical and non-technical audiences.

• Documentation: Produces clear technical design documents and deployment runbooks.

• Experience: 3–5 years of hands-on engineering experience, including at least 2 years building AI or ML solutions on Azure.

• Education: Bachelor's degree in Computer Science, Engineering, Data Science, or a rela