Learn by Doing. Become an AI Engineer.
English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 2 Lessons (4h 53m) | 768 MB
This course is designed for those who want to go beyond studying theory and build real artificial intelligence systems with their own hands. From language models to multimodal agents, you will follow the entire path of an AI engineer, creating working projects at each stage of your training.
Course Outline (Project-Based Learning)
Project 1. LLM Playground
- Building your own sandbox for working with LLM
- Fundamentals of language models: tokenization, architectures (GPT, Llama), text generation methods
- Post-training: SFT, RLHF
- Quality assessment methods: metrics, benchmarks, human evaluation
Project 2. Customer support chatbot based on RAG and Prompt Engineering
- Model adaptation practices: fine-tuning, PEFT, LoRA
- Prompt engineering techniques: few-shot, zero-shot, chain-of-thought
- Retrieval-Augmented Generation: search, indexing, generation
- Quality assessment of RAG systems
Project 3. “Ask-the-Web” Agent
- Building an agent that works with tools and the web
- Agent systems: planning, reflection, multi-process workflows
- Tool calling and multi-agent approaches
- Methods for evaluating agent effectiveness
Project 4. Deep Research with search and reasoning models
- Working with modern reasoning LLMs (e.g., OpenAI o1, DeepSeek-R1)
- Inference methods: CoT, Tree of Thoughts, self-consistency
- Training on reasoning data: SFT, RL with verifier, self-refinement
Project 5. Multimodal agent (text – image/video)
- Image and video generation: diffusion, GAN, VAE
- Architectures and training of diffusion models (U-Net, DiT)
- Methods for evaluating generation quality: IS, FID, CLIP
- Building end-to-end T2I and T2V systems
BLARETRFFDBEYADOIENRGHTAUDENRGTTETR

you must be registered member to see linkes Register Now