European Agentic AI Bootcamp

Agentic AI employs sophisticated reasoning to solve complex problems, utilizing data from multiple sources to analyze, strategize, and complete tasks independently. There are many powerful building blocks that developers and researchers can use to enable and accelerate the development and deployment of their agentic AI workflows.

The European Agentic AI Bootcamp covers some of these powerful tools, including Agent Skills, which are folders of instructions, scripts, and resources that agents can discover to grant them domain expertise and new capabilities; Model Context Protocol (MCP), an open protocol providing a standardized method for connecting AI models to various data sources and tools; NVIDIA® NIM™, a set of easy-to-use microservices that provides pre-optimized models and industry-standard APIs for building powerful AI agents, co-pilots, chatbots, and assistants; LangGraph, an orchestration framework for complex, stateful, and cyclic workflows for AI agents; and NeMo Agent Toolkit , an open-source library and framework designed to build, evaluate, and optimize production-ready, autonomous AI agents.

Attendees are guided through the creation of Agent Skills, HTTP-based MCP clients/servers, and the integration of both technologies into LLM workflows orchestrated with LangGraph and NeMo Agent Toolkit, powered by Nvidia NIM microservices. Attendees will then apply these learned skills in a hands-on challenge to modify an existing LLM workflow.

Why join this bootcamp:

Build a practical AI agent for a real use case.
Learn reusable patterns your team can adapt quickly.
Reduce the risk of investing in the wrong architecture.
Understand how to evaluate quality, latency, and performance early.
Get hands-on guidance.

SMEs and startups are especially encouraged to join this bootcamp.

This bootcamp would especially benefit the participants who are interested in optimizing and accelerating their applications further with domain experts by their side at the upcoming European AI Hackathon which is open for application submissions.

This bootcamp is co-organized by Austrian Scientific Computing (ASC), the Leibniz Supercomputing Centre (LRZ), the High-Performance Computing Center Stuttgart (HLRS), the Academic Computer Centre Cyfronet AGH (Cyfronet), OpenACC organization, and NVIDIA for AI Factory Austria AI:AT, HammerHAI, and Gaia AI Factory.

Anmeldung

Veranstaltungsbeginn

20. Juli 2026
10:00

Verstaltungsende

22. Juli 2026
16:15

Sprache

Englisch

Einstiegslevel

Basis

Mittel

Themenbereiche

Bootcamp/Hackathon

Daten in HPC / Deep Learning / Maschinelles Lernen

Themen

Künstliche Intelligenz

Python

Zurück zur Liste

Prerequisites and content levels

Prerequisites

Python, uv package and project manager
No GPU Programming knowledge is required.

Target audience

This course is intended for, but not limited to:

Small and medium-sized enterprise (SMEs), startups, industry practitioners, and researchers across Europe building AI-driven products and services.

Instructors

Main mentors: NVIDIA engineers and additional expert mentors will be announced soon.

Agenda

CE(S)T time zone

Day 0: Monday, 20 July // 10:00 AM - 11:00 AM

10:00 AM - 11:00 AM: Cluster Dry Run

Day 1: Tuesday, 21 July // 9 AM - 4:15 PM

09:00 AM - 09:15 AM: Welcome and Introductions
09:15 AM - 09:45 AM: Introduction to Agentic AI [Lecture]
10:30 AM - 12:00 PM: NVIDIA NIM, MCP Server, and Skills [Lab]
12:00 PM - 12:30 PM: Lunch Break
12:30 PM - 04:00 PM: LangGraph and NeMo Agent Toolkit [Lab]
04:00 PM - 04:15 PM: Wrap up and Q&A

Day 2: Wednesday, 22 July // 9 AM - 4:15 PM

09:00 AM - 09:30 AM: Introduction to the problem statement and Leaderboard
09:30 AM - 03:30 PM: Participants work on the problem statement
12:00 PM - 12:30 PM: Lunch break
03:30 PM - 03:40 PM: Call to Action: European AI Hackathon
03:40 PM - 04:00 PM: Project Discussions
04:00 PM - 04:15 PM: Wrap up and Q&A

Registration information

Apply for this course via the button at the top of this page.

Please note that by clicking the “Apply” button, you will be redirected to Open Hackathons, an external website that is outside the HLRS area of responsibility.

Registration closes on June 20, 2026.

Late applications may still be accepted depending on course capacity.

Fees

This course is free of charge.

The following applies only to accepted participants according to the Prerequisites above.

Contact

Junghwa Lee (HLRS), phone 0711 685 87228, training(at)hlrs.de

Further courses and training team

See the training overview and the Supercomputing Academy pages.
See also information about the HLRS training department and staff.

HLRS Training Collaborations in HPC and AI

HLRS is part of the Gauss Centre for Supercomputing (GCS), together with JSC in Jülich and LRZ in Garching near Munich. SIDE is the German National Competence Centre (NCC) for High-Performance Computing. HLRS is also a member of the Baden-Württemberg initiative bwHPC.
Since 2025, HLRS has been coordinating one of the AI Factories of the EuroHPC JU: HammerHAI.

Acknowledgements

This event is offered as part of HammerHAI, Germany’s first AI Factory, which has a dedicated focus on industry, manufacturing, engineering, and research. HammerHAI provides AI resources and solutions, an upcoming AI-optimized supercomputer, and personalized expert support for AI users at all stages in the AI lifecycle. This project has received funding from the European High Performance Computing Joint Undertaking under grant agreement No. 101234027. This project is co-funded by the European Commission, the German Federal Ministry of Research, Technology and Space (BMFTR), the Baden-Württemberg Ministry of Science, Research and the Arts, the Bavarian State Ministry of Science and the Arts and the Lower Saxony Ministry of Science and Culture.