Model Online / On-Site
Duration
Modules 6 modules

Course Objective & Scope

For organisations on Microsoft Azure, Azure OpenAI Service and Azure AI Foundry provide enterprise access to OpenAI models and open model catalogues with regional data residency, Entra ID governance and virtual network isolation. This course covers Azure OpenAI APIs, enterprise RAG with Azure AI Search, Azure AI Content Safety and evaluation/tracing in Foundry.

Participants implement keyless authentication with Managed Identity, design multi-region load balancing behind Azure API Management (APIM), and build a production-ready service on an internal scenario.

Who Should Attend?

  • Software and AI engineers building on Azure with Python, C#/.NET or TypeScript
  • Cloud architects responsible for Azure landing zones, security and APIM/network design
  • Technical teams building AI solutions integrated with the Microsoft data ecosystem
  • Prerequisite: familiarity with core Azure services and experience building REST APIs

Key Takeaways

  • Manage Azure AI Foundry projects, deployment types (Global Standard, DataZone, PTU) and model lifecycle
  • Implement Structured Outputs, tool calling and reasoning models with Azure OpenAI SDKs
  • Build permission-aware enterprise RAG with Azure AI Search (hybrid search + semantic ranker)
  • Secure workloads with Entra ID Managed Identity, Private Endpoints and Azure API Management
  • Validate safety and quality using Azure AI Content Safety, Prompt Shields and Foundry Evaluation

Curriculum

Azure AI Foundry and Azure OpenAI Deployment Models
  • Foundry hubs and projects, OpenAI models and the broader model catalogue
  • Standard, DataZone, Global and Provisioned Throughput (PTU) deployments
Application Development: Responses API, Structured Outputs and Tools
  • Streaming, schema-enforced outputs and tool calling with Python and .NET SDKs
  • Prompt caching and Batch API usage for cost and latency optimisation on Azure
Enterprise RAG with Azure AI Search
  • Integrated vectorization, hybrid search and Semantic Ranker configuration
  • Document-level security trimming and grounded responses with citations
Azure AI Content Safety and Evaluation
  • Content filters, Prompt Shields (jailbreak and indirect attack detection) and Groundedness detection
  • Azure AI Evaluation SDK and tracing with Application Insights and OpenTelemetry
Enterprise Security, Networking and APIM Gateway Architecture
  • Keyless authentication with Microsoft Entra ID, RBAC and Managed Identity
  • Private Endpoints, VNet integration and multi-region load balancing with Azure API Management
Hands-On: Production-Ready AI Service on Azure
  • Building a Foundry + AI Search + APIM reference application for an internal scenario
  • Capacity sizing (TPM/PTU) and security review checklist

Other Courses in This Category

  • Building Enterprise LLM Applications on Google Cloud Vertex AI

    Hands-on programme for building enterprise AI applications on Google Cloud Vertex AI using Gemini models, the Google Gen AI SDK, Context Caching, Grounding, Vertex AI Search, BigQuery and VPC-SC security.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • Production Architecture Patterns for Enterprise LLM Systems

    Architectural patterns for turning LLM prototypes into resilient enterprise systems: AI gateways, async queues, circuit breakers, fallback chains, idempotency, guardrails and OpenTelemetry tracing.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • Large Language Model (LLM) Fundamentals

    How foundation models and LLMs work: tokens, context windows, sampling, hallucination, model families and when to choose prompting, RAG or fine-tuning — a hands-on starting point for technical teams.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • Large Language Models and the Transformer Architecture

    A technical deep dive into the transformer: tokenization, self-attention, RoPE, KV cache, scaling laws, SFT, RLHF/DPO and reasoning models, explored hands-on with PyTorch and Hugging Face Transformers.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • Building Applications with LLM APIs

    Hands-on programme for building a near-production LLM application with the OpenAI, Anthropic Claude and Google Gemini APIs, covering streaming, conversation state, retries, rate limits, fallbacks and basic evals.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • Structured Outputs with LLMs: JSON Schema, Pydantic and Constrained Decoding

    Getting reliable JSON from LLMs with JSON Schema, OpenAI Structured Outputs, Gemini response schemas, Pydantic/Zod, Instructor and constrained decoding, plus validation, repair loops and document data extraction.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View

Get in touch