“Operating AI Systems with Spring AI” is a focused course that takes developers from building AI applications to running them confidently in production. The course covers embeddings, vector databases, and RAG pipelines in depth, while placing strong emphasis on performance, cost management, reliability, and observability by equipping students with the skills to maintain and operate AI services under real-world conditions.

By the end of this module, participants will be able to:

• Understand and manage the full request lifecycle of a production AI service, including interactions between LLMs and vector databases
• Generate, store, and retrieve embeddings efficiently while balancing cost and performance
• Set up and operate vector databases with filtering, indexing, and Spring AI integration
• Build and tune RAG pipelines using embeddings, including handling edge cases like missing or irrelevant context
• Apply caching, streaming, and context-size strategies to optimize latency and cost
• Design AI services with safe, predictable defaults and graceful degradation under failure
• Monitor AI system health through token usage, latency, vector DB metrics, and anomaly detection

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

• Ideally, completion of “Building AI Systems with Spring AI” or equivalent hands-on experience with Spring AI
• Familiarity with Spring Boot and REST service development
• Basic understanding of LLMs, prompt engineering, and RAG concepts
• Some exposure to Docker and cloud infrastructure is beneficial for deployment and operations topics

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