School of Software Engineering Training (SSE25)

This course has now reached capacity but please email GLAD@GEANT.org to be added to the waitlist.

Generative AI Buzz-Free Programming with LLMs

This training provides a pragmatic, no-nonsense approach to working with Large Language Models (LLMs). Instead of relying on hype, it emphasizes foundational techniques—effective prompts, solid context management, and time-tested programming principles.
Participants will gain insights into building reliable and maintainable LLM-based applications using SpringAI or LangChain, without unnecessary complexity.
Additionally, the course covers evaluating LLM outputs, implementing observability practices, and managing deployment and scaling concerns. By the end of the training, participants will be equipped to deliver robust, efficient, and production-ready LLM solutions.

The training follows a hands-on approach where participants work on real-world LLM integration challenges. The workshop components include guided exercises building actual LLM-powered applications, from simple prompt engineering to complex multi-step workflows.
 

Participants will learn through practical implementation how to avoid unnecessary complexity while delivering robust solutions that meet business requirements. Each module builds upon previous knowledge, culminating in the development of production-ready LLM applications that demonstrate best practices in testing, observability, and scalability.
 

By focusing on pragmatic techniques rather than theoretical abstractions, participants will leave with immediately applicable skills for implementing LLM solutions in their organizations. 

Requirements: 

• the participant has a minimum of 2 years of experience in the creating of IT systems (technical or non-technical)
• Python or Java environment, own computer with setup IDE, access to internet

Programme:

MODULE 1: CORE FOUNDATIONS OF LLM INTEGRATION

MODULE 2: PROMPT ENGINEERING ESSENTIALS

MODULE 3: CONTEXT MANAGEMENT AND STATE HANDLING

MODULE 4: LEVERAGING CLASSICAL PROGRAMMING APPROACHES

MODULE 5: AVOIDING OVERHEAD: MINIMIZING AGENTS AND ABSTRACTIONS

MODULE 6: REAL-WORLD IMPLEMENTATIONS WITH SPRINGAI AND LANGCHAIN

MODULE 7: EVALUATION AND TESTING OF LLM-BASED SYSTEMS

MODULE 8: OBSERVABILITY, DEPLOYMENT, AND SCALING

Key Takeaways:

• Master essential skills for working with LLMs without falling into hype-driven
• complexity
• Craft effective prompts and manage context to achieve accurate, consistent results
• Test, observe, deploy, and scale LLM-based applications using robust programming
• principles
• Know when to rely on direct techniques vs. introducing agents, tools, or abstractions
• Deliver production-ready, maintainable, and scalable LLM solutions with confidence

Please note: This is an in-person training event, and attendance is required for all three days.

Eligible participants can claim their time and travel for this workshop through the GN5 project.  See guidelines and eligibility criteria here:
https://wiki.geant.org/display/G52W1/Funding+to+Travel+for+Training