Annotation
Building trustworthy and capable agentic AI systems requires open innovation, scalable computing, and transparent design. This workshop explores how open-source initiatives—with AMD as a key driver—are accelerating the development of autonomous AI agents. It also highlights how AMD Agent Computers with integrated GPUs support efficient on-device inference and agentic workloads.
Participants will follow the evolution from token generation to AI agents, refresh the fundamentals of context engineering and RAG, and explore the main components of an AI agent: the model, orchestration, and tools. Guided hands-on labs will be delivered through the AUP Learning Cloud.
Benefits for the attendees
By the end of the workshop, participants will:
- Understand how generative AI has evolved into agentic systems.
- Learn how context engineering, RAG, models, orchestration, and tools work together.
- Gain hands-on experience with agentic AI concepts through practical labs.
- Understand how integrated GPUs support efficient on-device AI workloads.
- Gain knowledge applicable to research, education, and future AI projects.
Level
Introductory to intermediate
Language
English
Prerequisites
- Basic familiarity with AI and generative AI is recommended.
- Basic Python knowledge is helpful but not required. Participants need a computer, a stable internet connection, and an up-to-date web browser.
Tutor
Jens Stapelfeldt is the Global AI Lead for the AMD University Program (AUP), where he works with universities worldwide to enable hands-on AI education using open-source software and high-performance computing platforms. He focuses on helping educators quickly deploy modern AI workflows—from large language models and agentic systems to GPU-accelerated computing—without the burden of building infrastructure from scratch. Jens brings more than 30 years of experience in the semiconductor and microelectronics industry, spanning technical training, system architecture, and business leadership roles at AMD, Xilinx, Texas Instruments, and Doulos. He is passionate about bridging industry technology and academic learning to prepare the next generation of AI practitioners.
Dr. Mario Ruiz is a Senior Member of Technical Staff in the AMD University Program, where he supports academics in adopting the latest AMD tools and technologies. He manages the Heterogeneous Accelerated Compute Cluster and brings over 10 years of experience designing high-performance FPGA and SoC implementations. For the past six years, he has worked closely with academics and researchers to maximize performance and efficiency with AMD and Xilinx technologies through direct support and training. Before joining AMD, Mario earned his PhD from the Autonomous University of Madrid, where his research focused on High-Level Synthesis for high-speed networking. His expertise spans electronics, digital design, and computer architecture, with a strong interest in heterogeneous accelerated computing.
LUMI AI Factory is funded jointly by the EuroHPC Joint Undertaking, through the European Union's Connecting Europe Facility and the Horizon 2020 research and innovation programme, as well as Finland, the Czech Republic, Poland, Estonia, Norway, and Denmark.
This course was supported by the Ministry of Education, Youth and Sports of the Czech Republic through the e-INFRA CZ (ID:90254).
.png)
All presentations and educational materials of this course are provided under the Creative Commons Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) license.