Generative AI for Developers

ʼI‘m glad to share that I have successfully completed the Generative AI for Developers course

This journey has been an incredible learning experience, deepening my knowledge of Generative AI, LLM applications, and AI-powered development workflows. The course covered essential concepts and hands-on projects, allowing me to work with cutting-edge AI frameworks and best practices for real-world AI applications.

💡 Key Topics & Technologies Explored:

– Building Generative AI Applications (RAGs, Fine-tuning, APIs)
– AI Model Deployment & MLOps Best Practices
– Cloud Infrastructure for AI & Data Engineering
– Automated Testing for LLMOps
– Advanced Prompt Engineering & Model Evaluation
– AWS & Cloud-Based AI Services

Beyond just learning, I had the honor of contributing back as a guest lecturer in one of the course workshops, sharing insights and experiences with fellow learners! 🎤💡

A huge thank you to SET University, Artem Kobrin, Rostyslav Myronenko Heorhii Kalaichev and other instructors for designing such a fantastic program! Looking forward to applying this knowledge in future AI-driven projects.  

I’m satisfied with the course; it was quite informative. I had the opportunity to ask the instructors many questions on topics that interested me, which was probably the most important thing for me. The theoretical sessions were good, but the initial topics were very basic for beginners, in my opinion. Toward the end, though, there were truly challenging and interesting topics.

As for advice, I’d only say that before each lesson, it’s better to do some self-study—Google, read about the topic that will be covered. That way, the material will be much easier to remember, especially during the later lessons.

I’ll start with a bit about myself. I work as a Data Engineer (5+ years). I have also worked with an ML engineers & Data Scientists team. But that’s basically all my “ML experience.” Then, when LLMs appeared, the company decided to develop expertise in AI. We tried to find an AI engineer, but ran into the issue that it wasn’t clear what knowledge and skills such a specialist should have. But it became apparent that there is a “classic” ML specialist and a specialist in LLMs. That’s how my deep dive into ML, including LLM, began. There’s a lot of information, but it needed to be consolidated somehow, and we needed examples of how different technologies could be applied. That’s why we found your course.

Overall impressions of the program
Overall, the course is great and definitely very useful. Of course, there were moments when not everything worked out for everyone (both attendees and instructors). But these moments showed how to quickly find and solve problems. For me personally, as someone not closely involved with AI, there was a lot of new information—I even had doubts that I would understand everything at all. However, the materials and workshops conducted by speakers with real project experience helped me sort through it all. I’d like to single out the final projects in particular; some of them were really impressive.

Main insights I gained during the training
Before the course, LLM-related projects seemed incredibly complex. After completing it, I can’t say everything is easy, but it has all become clear. AI projects stopped being a “black box.” The final projects demonstrated a very broad, and sometimes unexpected, spectrum of possibilities for using LLMs.

Advice for future course students
Don’t be afraid to ask questions. The worst question is the one you don’t ask. Present your own ideas and projects, even if they’re not perfect. Expert feedback will help you choose a path for improving your idea or the next step for your own project. Believe in yourselves—you can do it!