AI Engineering using Java & Spring Framework

Description

This course equips Java professionals with the skills to design, build, and operate AI-powered applications using Spring AI. Participants gain the practical capability to design reliable LLM-powered services, integrate intelligent retrieval mechanisms, orchestrate AI agents, and manage performance, cost, and operational risk. By the end of the program, they will be equipped to drive AI integration initiatives and confidently engineer production-ready AI systems.

Indicative Duration: 20 training hours
*Duration is adjusted based on the final scope and the target audience.

Scope

1. Building AI Systems with Spring AI	1.1 Spring AI Core Concepts	AI vs traditional services Spring AI architecture ChatClient Models/messages System vs user instructions
	1.2 Prompt Engineering	Prompt templates Instruction vs context Few-shot prompting Structured outputs
	1.3 Conversational AI & Memory	Stateless vs stateful conversations Memory patterns (sliding window, summary, store-backed) Memory lifecycle
	1.4 RAG Foundations & Basic Monitoring	LLM hallucinations, RAG pipeline overview query→retrieval→context→generation Chunking strategies Logging Token usage monitoring
	1.5 Tool Calling & MCP	Tools vs APIs Validation Error handling Multi-step flows MCP client/server basics
	1.6 Offline & Hybrid LLM Deployment	Cloud vs offline models Model selection & quantization Docker deployment Switching between cloud/local
2. Operating AI Systems with Spring AI	2.1 AI Systems in Production	Stateless vs stateful services Request lifecycle LLM & vector DB interactions
	2.2 Embeddings: Concepts & Usage	What embeddings are Generation Storage/retrieval Cost/performance basics
	2.3 Vector Databases: Foundations	Vector search/indexing basics Metadata filtering Common stores Integration with Spring AI
	2.4 RAG with Embeddings	Using embeddings in RAG Building simple RAG pipelines Context assembly Handling missing/irrelevant results
	2.5 Performance, Cost & Safe Defaults	Context size vs latency Caching embeddings/responses Streaming vs non-streaming LLM/vector DB unavailability Predictable response design
	2.6 Operations & Monitoring	AI service health metrics Token/embedding usage Latency monitoring Vector database monitoring Logging Anomaly detection
3. Agentic AI with Spring AI & Embabel	3.1 Introduction to Agentic AI	What agentic AI is The differences between agents and chatbots Use cases Decision-making loops
	3.2 Spring AI Agents Basics	Creating AI agents in Spring AI Agent lifecycle Instructions vs autonomy Connecting agents to models
	3.3 Embeddings & Context for Agents	Using embeddings for agent memory and knowledge retrieval Context assembly RAG for agents
	3.4 Tool Integration & MCP for Agents	Exposing tools to agents MCP client/server usage Multi-step tool orchestration Action planning
	3.5 Running Agentic AI Safely	Sandbox execution Fallback strategies Monitoring agent actions Logging and observability Basic operational considerations

Learning Objectives

Upon completion of the course participants will be able to:

Explain the architecture and core concepts behind AI-enabled services using Spring AI and Java
Apply foundational prompt engineering techniques for structured and reliable outputs
Implement guided examples of Retrieval-Augmented Generation (RAG) pipelines
Understand the principles of agentic AI systems with tool orchestration and controlled autonomy
Identify key practices for monitoring, optimizing, and safeguarding AI systems in production

Target Audience

Roles: Backend Engineers, Software Architects, Technical Leads, Solution Architects
Seniority: Mid-Level to Senior Professionals

Prerequisite Knowledge

Solid understanding of Java (Java 21+ recommended)
Experience with Spring Boot and Spring Framework fundamentals (configuration, dependency injection, REST controllers)
Basic knowledge of HTTP/REST APIs
Familiarity with JSON and structured data formats
Basic understanding of Docker concepts (images, containers, running services)

Delivery Method

Sessions can be delivered via the following formats:

Live Online – Interactive virtual sessions via video conferencing
On-Site – At your organization’s premises
In-Person – At Code.Hub’s training center
Hybrid – A combination of online and in-person sessions

The training methodology combines presentations, live demonstrations, hands-on exercises and interactive discussions to ensure participants actively practice AI in realistic work scenarios.

Tags: AI Engineering, Generative & Agentic AI

Date

On Demand

Organizer

Code.Hub

Email

[email protected]