A curated collection of resources, courses, books, and tools covering AI systems, ML, LLMs, generative AI, and agentic AI.
Snapshot for reference; my personal notes live elsewhere.
- Mathematics for Machine Learning and Data Science Specialization
- Machine Learning Specialization
- Deep Learning Specialization
- Machine Learning in Production
- Full Stack Deep Learning 2022
- Hugging Face LLM Course: Link
- Neural Networks: Zero to Hero (Andrej Karpathy): YouTube Playlist
- Optional: Stanford CS25 Recordings (very academic)
- Designing Machine Learning Systems: An Iterative Process for Production‑Ready Applications — Chip Huyen
- AI Engineering: Building Applications with Foundation Models — Chip Huyen
- Building LLMs for Production: Reliability, Scaling & Fine‑Tuning — (various authors)
- Effective Python: 90 Specific Ways to Write Better Python — Brett Slatkin
- Optional:
- Mathematics for Machine Learning — Deisenroth, Faisal & Ong (optional)
- OpenAI Cookbook
- FastAPI, uvicorn, Pydantic
- Reasoning Models / Multi-Modal Models
- Unsloth
- Prompting techniques: Chain of Thought, Tree of Thought, Few-shot, Self-consistency, Reflection, ReAct
- Generative AI / Agentic AI
- Databricks / Spark for ML
- Kubernetes (kagent, kgateway)
- Vector databases & indexes: Flat, IVFFlat, HNSW, Postgres pgvector
- RAG and Agentic RAG
- MCP
- LLM Orchestration: LangChain/LangGraph, CrewAI, LlamaIndex; test Agent SDKs from hyper-scalers and AI Labs
- AI Agent & Multi-Agent Design Patterns: ReAct, Task Decomposition, Reflection, Planner-Executor, Critic-Actor, Hierarchical, Collaborative
- Long & short memory in agentic systems + mem0
- A2A, ACP, Internet of Agents
- Agent Orchestration Frameworks
- Azure AI Studio / Google Vertex AI / AWS Bedrock
- CICD / Unit Evaluation Tests
- liteLLM, Orq, Martian
- LLM Observability: Langsmith SDK / Opik SDK / OpenTelemetry
- Evaluation Techniques
- Security: GuardrailsAI
- OpenAI platform docs: deploy, fine-tune, embed
- Cursor / Codex / Claude Code / ZenCoder
- Prompt Engineering for Developers
- MCP: Build Rich Context AI Apps with Anthropic
- Google Startup School - Gen AI
- Google Startup School - Agentic AI
- AI Engineer Toolkit
Anthropic Free Courses
- Prompt Engineering
- Building Effective Agents
- Best Practices for Agentic Coding
- The AI Fluency Framework
- Build with Claude
- Claude for Work
- Anthropic API Fundamentals
- Real World Prompting
- Prompt Evaluations
- A2A and MCP
- MCP Paper
- RL Survey for Large Reasoning Models
- Repos to Learn AI
- AI Engineering Blogs: Link
- Agents Whitepaper — foundational whitepaper
- Agents Towards Production — one-stop repo to understand agentic systems
- Agentic Design Patterns (Book) — design patterns for multi-agent systems
- A2A Orchestration — agent-to-agent orchestration framework
- Effective Context Engineering — best practices for session & memory management in agents
- Context Engineering Summary — practical notes on sessions & memory (Nov 2025)
- Attention is All You Need (Original Paper) — original Transformer paper
- How Transformers Work – Harvard NLP — most detailed explanation
- The Transformer Family – Lilian Weng — tracks evolution to LLMs
- Illustrated Transformer – Jay Alammar — highly illustrative, visual
- How Transformer LLMs Work (Short Course) — course overview
- Ring Attention — specialized attention mechanism
- Mixture of Experts — MOE architectures, scaling & routing
- ByteByteAI — AI / system design content
- Andrej Karpathy — channel with deep learning insights
- Aishwarya Reganti — TOP resource sharer
- Meri Nova
- Jay Alammar
- Chip Huyen — deep ML & AI systems writing
- LatentSpace — AI/ML research & insights newsletter
- Pragmatic Engineer Newsletter — engineering leadership & systems
- ByteByteGo Newsletter — systems design & AI insights
- The Batch (DeepLearning.AI) — weekly deep learning news
- Swirl AI Newsletter — AI industry newsletter
- Gradient Flow — data, machine learning & AI analysis by Ben Lorica
- Data Engineering Weekly — weekly data engineering newsletter by Ananth Packkildurai
- Big Technology by Alex Kantrowitz — tech & AI industry insights
- LatentSpace Podcast — interviews & insights in AI/ML
- 60 AI Projects for Practice (pick 1–3 max)
- Machine Learning System Design Interview — Ali Aminian & Alex Xu
- Generative AI System Design Interview — Ali Aminian & Hao Sheng
- Upload documents (PDFs/Markdown)
- Chunk documents (e.g., LangChain TextSplitter)
- Create embeddings
- Store in vector DB
- Query: retrieve relevant chunks
- Feed context + query to LLM (OpenAI/Mistral)
- Return answer
- REST API + UI (dockerized)
- Add feedback loop for tuning
- Explore open-source models (Mistral, LLaMA2) + fine-tuning via LoRA
Other ideas:
- Experiment with Kubeflow + GPU
- Fine-tune a model on HuggingFace