Model Online / On-Site
Duration
Modules 6 modules

Course Objective & Scope

Core systems in banking, insurance, telecoms and enterprise software largely run on Java (Spring Boot, Quarkus) or .NET, and introducing a separate Python stack just to call LLMs adds unnecessary operational friction. This course covers building AI features directly inside enterprise stacks using Spring AI and LangChain4j on Java, and `Microsoft.Extensions.AI` and Semantic Kernel on .NET.

Tailored to the organisation's stack (Java-focused, .NET-focused or dual-stack), the programme guides participants in building a production-ready LLM service integrated with enterprise dependency injection, security, OpenTelemetry and data stores.

Who Should Attend?

  • Software engineers building enterprise backends in Java (Spring Boot) or C#/.NET
  • Solution architects adding LLM, RAG and agent capabilities to existing microservices
  • Platform teams defining AI engineering standards for non-Python enterprise stacks
  • Prerequisite: enterprise application development experience in Java/Spring or C#/.NET

Key Takeaways

  • Configure provider-agnostic LLM clients with Spring AI, LangChain4j or Semantic Kernel/`Microsoft.Extensions.AI`
  • Map LLM responses directly into strongly typed Java Records/POJOs and C# classes
  • Expose existing business service methods safely as LLM tools/plugins and MCP endpoints
  • Implement RAG pipelines in Java or .NET using pgvector, Redis, Elasticsearch or Azure AI Search
  • Apply enterprise observability and resilience with OpenTelemetry, Micrometer and Resilience4j/Polly

Curriculum

AI Architectural Options for Enterprise Java and .NET
  • Native JVM/CLR integration versus a separate Python microservice
  • Positioning Spring AI, LangChain4j, `Microsoft.Extensions.AI` and Semantic Kernel
Chat Clients, Templates and Strongly Typed Outputs
  • Model clients via Dependency Injection, streaming and chat memory
  • Java Records / BeanOutputConverter and C# strongly typed schema binding
Tool Calling and MCP with Enterprise Services
  • Spring `@Tool`, LangChain4j `@Tool` and Semantic Kernel `KernelFunction` definitions
  • Transaction boundaries, user security context and MCP integration in service methods
RAG and Vector Stores in Java and .NET
  • Embeddings and integration with pgvector, Elasticsearch, Qdrant and Azure AI Search
  • Permission-aware retrieval using Advisor and filter pipelines
Production Resilience, Observability and Testing
  • Retries, circuit breakers, rate limiters and fallbacks with Resilience4j and Polly
  • Token and latency metrics via OpenTelemetry/Micrometer and testing with JUnit/xUnit
Hands-On: Adding LLM Capabilities to an Enterprise Microservice
  • Building an end-to-end AI endpoint inside the team's Java or .NET service template
  • Architecture review and production readiness checklist

Other Courses in This Category

  • Building Enterprise LLM Applications on Amazon Bedrock

    Hands-on programme for building enterprise generative AI solutions on AWS using the Amazon Bedrock Converse API, Knowledge Bases, Agents, Guardrails, IAM/VPC security and cost controls.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • Enterprise LLM Development with Azure OpenAI and Azure AI Foundry

    Building enterprise AI applications on Azure AI Foundry and Azure OpenAI Service with GPT and reasoning models, Azure AI Search, Entra ID authentication, Private Endpoints, Content Safety and PTU/quota management.

    LLM Application Engineering Corporate
    Live Course
    6 modules
    View
  • 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

Get in touch