ByteByteAI Logo

Taught by Best-Selling
Author Ali Aminian

Amazon Best Sellers

Meet Your Instructor

Ali Aminian Profile

Ali Aminian

Ali Aminian is a best-selling author of multiple books on machine learning and generative AI. With over a decade of experience at leading tech companies, he has built AI systems that are intelligent, safe, and efficient. He also contributes to AI courses at Stanford University, combining technical expertise with a passion for teaching.

Adobe Google Stanford
button icon Start Enrollment

Course Outline (Project-Based Learning)

Project 1

Build an LLM Playground

LLM Overview and Foundations
Pre-Training
  • Data collection (manual crawling, Common Crawl)
  • Data cleaning (RefinedWeb, Dolma, FineWeb)
  • Tokenization (e.g., BPE)
  • Architecture (neural networks, Transformers, GPT family, Llama family)
  • Text generation (greedy and beam search, top-k, top-p)
Post-Training
  • SFT
  • RL and RLHF (verifiable tasks, reward models, PPO, etc.)
Evaluation
  • Traditional metrics
  • Task-specific benchmarks
  • Human evaluation and leaderboards
Chatbots' Overall Design
Project 1
Project 2

Build a Customer Support Chatbot using RAGs and Prompt Engineering

Overview of Adaptation Techniques
Finetuning
  • Parameter-efficient fine-tuning (PEFT)
  • Adapters and LoRA
Prompt Engineering
  • Few-shot and zero-shot prompting
  • Chain-of-thought prompting
  • Role-specific and user-context prompting
RAGs Overview
Retrieval
  • Document parsing (rule-based, AI-based) and chunking strategies
  • Indexing (keyword, full-text, knowledge-based, vector-based, embedding models)
Generation
  • Search methods (exact and approximate nearest neighbor)
  • Prompt engineering for RAGs
RAFT: Training technique for RAGs
Evaluation (context relevance, faithfulness, answer correctness)
RAGs' Overall Design
Project 2
Project 3

Build an "Ask-the-Web" Agent similar to Perplexity with Tool calling

Agents Overview
  • Agents vs. agentic systems vs. LLMs
  • Agency levels (e.g., workflows, multi-step agents)
Workflows
  • Prompt chaining
  • Routing
  • Parallelization (sectioning, voting)
  • Reflection
  • Orchestration-worker
Tools
  • Tool calling
  • Tool formatting
  • Tool execution
  • MCP
Multi-Step Agents
  • Planning autonomy
  • ReACT
  • Reflexion, ReWOO, etc.
  • Tree search for agents
Multi-Agent Systems (challenges, use-cases, A2A protocol)
Evaluation of agents
Project 3
Project 4

Build "Deep Research" Capability with Web Search and Reasoning Models

Reasoning and Thinking LLMs
  • Overview of reasoning models like OpenAI's "o" family and DeepSeek-R1
Inference-time Techniques
  • Inferece-time scaling
  • CoT prompting
  • Self-consistency
  • Sequential revision
  • Tree of Thoughts (ToT)
  • Search against a verifier
Training-time techniques
  • SFT on reasoning data (e.g., STaR)
  • Reinforcement learning with a verifier
  • Reward modeling (ORM, PRM)
  • Self-refinement
  • Internalizing search (e.g., Meta-CoT)
Project 4
Project 5

Build a Multi-modal Generation Agent

Overview of Image and Video Generation
  • VAE
  • GANs
  • Auto-regressive models
  • Diffusion models
Text-to-Image (T2I)
  • Data preparation
  • Diffusion architectures (U-Net, DiT)
  • Diffusion training (forward process, backward process)
  • Diffusion sampling
  • Evaluation (image quality, diversity, image-text alignment, IS, FID, and CLIP score)
Text-to-Video (T2V)
  • Latent-diffusion modeling (LDM) and compression networks
  • Data preparation (filtering, standardization, video latent caching)
  • DiT architecture for videos
  • Large-scale training challenges
  • T2V's overall system
Project 5
Project 6

Capstone Project

  • Choose your own idea
  • Build with techniques from the course
  • Get real-time feedback from the instructor as you build
  • Demo + Feedback session
Project 6
button icon Start Enrollment

Is this course for you?

reason sticker

If you want to start learning Al from scratch,

check this is for you!

If you've learned some concepts but still feel confused,

check this is for you!

If you want to build a few neural
network models and agents quickly,

check this is for you!

If you are tired of learning
Al alone,

check this is for you!
button icon Start Enrollment

Course Highlights

Number badge 1 Structured, Systematic Learning Path

Highlight 1

Number badge 2 Intuitive, Visual Explanations

Highlight 2

Number badge 3 Project-Based Learning That Sticks

Highlight 3

Number badge 4 Beginner-Friendly Code that You can Run

Highlight 4

Number badge 5 Learn the 'Why' Behind the 'How'

Highlight 5
button icon Start Enrollment

What You'll Get

Live & Interactive Sessions

Learn directly from Ali Aminian in real time. Ask questions, get feedback, and stay engaged.

Lifetime Access to Course Content

Revisit lessons, recordings, and other resources anytime.

Peer Community

Stay motivated and accountable with a group of peers who are learning alongside you.

The ByteByteGo Guarantee

If you're not 100% satisfied within the first 7 days, you can request a full refund. No questions asked.

button icon Start Enrollment

FAQs

When are the live classes?

Build an AI Project with Ali (Live, Saturdays, 10–11:30 AM PT) and Office Hours (Live, Wednesdays, 5–6 PM PT).

Everything is recorded, so if you cannot attend live, you can watch the recordings later.

What if I miss a live session?

Every session is recorded, so you can catch up anytime that works for you.

What are the prerequisites?

Basic computer science fundamentals. Some understanding of Python can be helpful, but is not required.

What's the time commitment? Can I take this course while working full-time?

4–6 hours total per week: approximately 4–5 hours of lectures and project walkthroughs, plus 1 hour of optional coding practice or assignments.

What's the refund policy?

If you're not 100% satisfied within the first 7 days, you can request a full refund by sending an email to ai-course@bytebytego.com. No questions asked.

Got questions?

Reach out to ai-course@bytebytego.com. We'll get back to you within 24 hours.

button icon Start Enrollment