Course detail

Algorithmic Engineering and AI Cooperation

FSI-SAIAcad. year: 2026/2027

The course provides the foundations of algorithmic engineering methodology and an introduction to advanced cooperation with artificial intelligence tools. It introduces students to the principles of complex technical problem decomposition, exact prompting techniques, and the critical selection of technology stacks. The course presents autonomous agent architectures, advanced RAG systems, issues in heterogeneous system integration, and the deployment of models to end devices.

Language of instruction

Czech

Number of ECTS credits

4

Mode of study

Not applicable.

Entry knowledge

Knowledge of object-oriented programming principles (in any language), fundamentals of algorithmization, ability to mathematically formulate technical problems, and basic orientation in artificial intelligence principles and tools (completion of the SIS course or equivalent experience).

Rules for evaluation and completion of the course

The course assessment consists of points for a semester project (presentation of a complex system and defense of the architecture created in cooperation with AI) (70%) and points for regular independent tasks from exercises (30%). A condition for obtaining credit is earning at least 50% of the points from the semester project. Special credit may be awarded for active contribution during lessons.

Attendance at lectures is recommended, while attendance at exercises is 100% mandatory. Teaching follows the weekly schedule. The method for making up missed exercises is entirely at the discretion of the instructor.

Aims

To introduce students to the role of a solution architect in the AI era and teach them methods for effectively managing the development of complex systems in a multi-language environment. To teach advanced problem decomposition, verification techniques, technical auditing of generated code, and work within modern development environments. To familiarize students with multi-agent system architectures, semantic engineering, and the principles of on-device AI and hybrid computing systems.

Students will gain knowledge in the field of algorithmic engineering and cooperation with LLM models. They will learn to design the architecture of mathematical solutions, effectively integrate various technologies into functional units, and utilize AI for rapid prototyping as well as the optimization of computationally intensive algorithms while maintaining technical correctness.

Study aids

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

Albada Michael, Building Applications with AI Agents: Designing and Implementing Multiagents Systems. 2025, O'Reilly Media, Inc. ISBN: 978-1098176501. (EN)
Huyen Chip. AI Engineering: O'Reilly Media, Inc., 2024. ISBN: 9781098166304.  (EN)
Huyen Chip, Designing Machine Learning Systems. 2022, O'Reilly Media, Inc. ISNB: 9781098107932. (EN)

Recommended reading

ROTHMAN, D. a GULLI, A. Transformers for natural language processing: build, train, and fine-tune deep neural network architectures for NLP with Python, PyTorch, TensorFlow, BERT, and GPT-3. Birmingham: Packt, 2022. ISBN 978-1-80324-733-5. (EN)
up to date online articles, blogs with updates of OpenAI, Anthropic, Google (EN)

Classification of course in study plans

  • Programme N-MAI-P Master's 1 year of study, summer semester, compulsory-optional

Type of course unit

 

Lecture

13 hours, optionally

Teacher / Lecturer

Syllabus

  1. Engineering Collaboration Paradigm
  2. Abstraction and Decomposition
  3. Verification and Technical Audit
  4. Critical Perception and AI Debugging
  5. Autonomous Agent Architecture and Complex Task Planning
  6. Multi-agent Systems and Workflow
  7. Advanced RAG Systems and Semantic Engineering
  8. Integration of Heterogeneous Systems
  9. Modern Development Environments
  10. Hybrid Systems
  11. Local and Embedded AI
  12. Lecturer’s Reserve

Computer-assisted exercise

26 hours, compulsory

Teacher / Lecturer

Syllabus

Computer exercises are focused on the practical mastery of the topics covered in lectures, with an emphasis on engineering independence. Students learn to utilize AI not as a replacement for thinking, but as a high-performance collaborator in the design, implementation, and verification of complex systems. The main component of the course is work on a semester project that simulates an engineering workflow from problem decomposition to deployment on end devices.

1. Analysis and Decomposition

2. Professional Environment Configuration

3. - 5. Architecture and Prototyping

6 . - 8. Implementation of Intelligent Modules

9. Verification and Optimization

10. - 11. Finalization and Documentation

12. Consultation

13. Presentation