ByteByteAI Logo
Teach on ByteByteGo

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, DeepSeek, Qwen, Gemma)
  • 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)
Agent Evaluation
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
  • Inference-time scaling
  • CoT prompting
  • Parallel sampling
  • Sequential sampling
  • 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)
Local Deployment
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

Ship a portfolio-ready AI project from idea to demo
  • Choose: pick your own idea, or start from a curated list
  • Build: implement using techniques from the course
  • Iterate: get real-time feedback from the instructor as you build
  • Optional Demo: present your project on final demo day
Project 6
button icon Start Enrollment

Is this course for you?

reason sticker

If you want to start learning AI 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.

Certificate of Completion

Showcase your achievement on LinkedIn. Proof that you’ve leveled up with real-world skills.

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

ByteByteAI Bonuses!

Bonus 1:

Free access to all ByteByteGo digital books, valued at $500

Free access to digital books including Machine Learning System Design and AI Engineering guides

Bonus 2:

Get Exclusive ML Resources — Constantly Updated!

Exclusive machine learning resources and learning materials

FAQs

When are the live classes?

Here is the full live schedule. All times are Pacific Daylight Time (PDT), and every session is recorded.

Week 1

  • Sat, May 16, 4–5:30 PM: Intro & Logistics
  • Wed, May 20, 5–6 PM: Office Hour

Week 2

  • Sat, May 23, 10–11:30 AM: Deep Dive P1: LLM Playground
  • Wed, May 27, 5–6 PM: Office Hour

Week 3

  • Sat, May 30, 10–11:30 AM: Deep Dive P2: Customer Support Chatbot
  • Wed, Jun 3, 5–6 PM: Office Hour

Week 4

  • Sat, Jun 6, 10–11:30 AM: Deep Dive P3: Ask-the-Web Agent
  • Wed, Jun 10, 5–6 PM: Office Hour

Week 5

  • Sun, Jun 14, 10–11:30 AM: Deep Dive P4: Deep Research
  • Wed, Jun 17, 5–6 PM: Office Hour

Week 6

  • Sat, Jun 20, 10–11:30 AM: Deep Dive P5: Multi-Modal Agent
  • Sun, Jun 21, 10 AM–12 PM: Capstone Demo

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 knowledge and Python are required to complete the projects but not needed to follow the lectures and live coding sessions.

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

4–6 hours per week. About 4–5 hours of lectures and project walkthroughs, plus 1 optional hour for coding practice or assignments. If you're new to AI or Python, or want to explore extra project settings, it may take longer.

Exclusive Bonus for Cohort Students

If you purchase this cohort course, you'll receive free lifetime access to ByteByteGo.com (a $500 value).

Please note that if you already purchased ByteByteGo.com before joining the cohort, we will not be able to issue a refund. However, if you are currently on the yearly plan, you will be upgraded to the lifetime plan for free.

Just make sure to use the same email address you used to register for the cohort, and your ByteByteGo.com access will be activated automatically.

What's the refund policy?

If you are not 100 percent satisfied within the first 7 days after the first live session, you can request a full refund by emailing 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