Browse By Tag

Use this page to jump across the repo by tag instead of by folder or curriculum order.

Common ways to use it:

• follow a technical theme such as rag, llmops, evaluation, or multimodal
• scan by level with tags such as beginner, intermediate, or advanced
• move sideways across related implementation patterns without losing the broader curriculum

a2a

• Agentic Protocols

activation

• Neural Networks

adk

• Agentic Protocols

adversarial

• MCP Security

adversarial-ml

• Adversarial ML and AI Security

agent-eval

• Agent Evaluation

agent-protocols

• Agentic Protocols

agentic-ai

• AI Agents
• AI Coding Agents

agentic-ai-engineer

• Agentic AI Engineer

agentic-infra

• Agentic Protocols

agentic-rag

• Graph RAG

agentic-security

• MCP Security

agents

• AI Agents
• Agent Memory Systems
• Conversational AI
• Multi-Agent Architectures

ai

• Root Overview

ai-architecture

• AI System Design
• API Design for AI
• System Design for AI Interviews

ai-engineer

• AI Engineer
• Role Reference

ai-infra

• GPU and CUDA Programming

ai-product

• AI Coding Agents
• AI UX Patterns

ai-product-management

• AI Product Management Fundamentals

ai-security

• Safety and Governance Roles

alignment

• Ethics, Safety and Alignment
• RL Alignment

antigravity

• Code Generation

api

• API Design for AI

application-roles

• Application and Strategy Roles

applications

• AI Product Management Fundamentals
• API Design for AI

applied-ml

• Applied ML and Domain Roles

architecture

• Application and Strategy Roles
• Distributed Inference and Serving Architecture
• Modern Architectures
• State Space Models
• Transformers

async

• API Design for AI

attention

• Attention Deep Dive
• Attention Mechanism
• Transformers

autogen

• Agentic Protocols

automation

• CI/CD for ML

autonomy

• AI Agents

azure-ai-foundry

• Cloud ML Services

backpropagation

• Neural Networks

bayes

• Probability and Statistics for AI

benchmarks

• Evaluation and Benchmarks

bert

• NLP Fundamentals

bias

• Ethics, Safety and Alignment

bpe

• Tokenization

caching

• Cost Optimization

career

• AI Engineer
• Agentic AI Engineer
• Application and Strategy Roles
• Applied ML and Domain Roles
• Generative AI Engineer
• LLM Engineer
• ML Engineer
• MLOps / LLMOps Engineer
• RAG Engineer
• Research and Infrastructure Roles
• Role Reference
• Safety and Governance Roles

catastrophic-forgetting

• Continual Learning

chain-of-thought

• Prompt Engineering
• Reasoning Models

chatbots

• Conversational AI

checkpointing

• Distributed Training and Infrastructure

chinchilla

• Scaling Laws and Pretraining

chroma

• Vector Databases

chunking

• Document Parsing and Extraction
• Long-Context Engineering

ci-cd

• LLMOps

cicd

• CI/CD for ML

circuits

• Interpretability

classical-ml

• Classical ML for GenAI

claude

• LLMs Overview

claude-4

• LLM Landscape

claude-code

• Code Generation

cloud

• Cloud ML Services

clusters

• Distributed Training and Infrastructure

cnn

• Neural Networks

code-generation

• Code Generation

codex

• AI Coding Agents

coding-agents

• AI Coding Agents
• Code Generation

compliance

• AI Regulation

compression

• Distillation and Compression

compute

• Scaling Laws and Pretraining

computer-vision

• Applied ML and Domain Roles
• Computer Vision Fundamentals

consistency

• Distributed Systems for AI

constrained-decoding

• Structured Outputs

consulting

• Application and Strategy Roles

containers

• Docker and Kubernetes

content-filtering

• Guardrails and Content Filtering

context

• Agent Memory Systems

context-caching

• Context Engineering

context-window

• Context Engineering
• Long-Context Engineering

continual-learning

• Continual Learning

continuous-improvement

• Data Flywheel Design

contrastive-learning

• Embedding Fine-Tuning

conversation

• Agent Memory Systems

conversational-ai

• Applied ML and Domain Roles
• Conversational AI

coordination

• Multi-Agent Architectures

copilot

• Code Generation

cost

• Cost Optimization
• LLM Routing and Model Selection

crewai

• Agentic Protocols

cuda

• GPU and CUDA Programming

cursor

• AI Coding Agents
• Code Generation

cv

• Computer Vision Fundamentals

dall-e

• Diffusion Models

dare

• Model Merging

data-curation

• Synthetic Data and Data Engineering

data-engineering

• Applied ML and Domain Roles
• Synthetic Data and Data Engineering

data-flywheel

• Data Flywheel Design

data-mix

• Scaling Laws and Pretraining

data-versioning

• ML Experiment and Data Management

deep-learning

• Deep Learning Fundamentals
• Root Overview
• Transformers

deepeval

• LLM Evaluation Deep Dive

deepseek-r1

• Reasoning Models

deepspeed

• Distributed Training and Infrastructure

defense

• Prompt Injection Deep Dive

deployment

• CI/CD for ML
• Docker and Kubernetes
• LLMOps

design

• AI UX Patterns

detection

• Computer Vision Fundamentals

developer-tools

• AI Coding Agents

devin

• AI Coding Agents
• Code Generation

dialogue

• Conversational AI

diffusion

• Diffusion Models

digital-omnibus

• AI Regulation

distillation

• Distillation and Compression

distributed-inference

• Distributed Inference and Serving Architecture

distributed-systems

• Distributed Systems for AI

distributed-training

• Distributed Training and Infrastructure
• Research and Infrastructure Roles

distributions

• Probability and Statistics for AI

docker

• Docker and Kubernetes

document-parsing

• Document Parsing and Extraction

dot-product

• Linear Algebra for AI

dpo

• Advanced Fine-Tuning
• RL Alignment

dvc

• ML Experiment and Data Management

efficiency

• Distillation and Compression

embeddings

• Embedding Fine-Tuning
• Embeddings
• RAG
• Vector Databases

environment

• Python for AI

ethics

• Ethics, Safety and Alignment

eu-ai-act

• AI Regulation

evals

• Monitoring and Observability

evaluation

• AI Product Management Fundamentals
• Agent Evaluation
• Evaluation and Benchmarks
• LLM Evaluation Deep Dive
• Retrieval Evaluation
• System Design for AI Interviews

experiment-tracking

• ML Experiment and Data Management

experiments

• Research Methodology and Paper Reading

extraction

• Document Parsing and Extraction

factuality

• Hallucination Detection

feedback

• AI UX Patterns

feedback-loops

• Data Flywheel Design

few-shot

• Prompt Engineering

fine-tuning

• Advanced Fine-Tuning
• Embedding Fine-Tuning
• Fine-Tuning
• Model Merging

flash-attention

• Attention Deep Dive
• Modern Architectures

foundation-models

• Research and Infrastructure Roles

fsdp

• Distributed Training and Infrastructure

function-calling

• AI Agents
• Function Calling and Structured Output
• Structured Outputs

gemini

• LLMs Overview

gemini-3

• LLM Landscape

gemini-cli

• Code Generation

genai

• AI Engineer
• AI System Design
• Agentic AI Engineer
• Agentic Protocols
• Code Generation
• Context Engineering
• Continual Learning
• Diffusion Models
• Distillation and Compression
• Ethics, Safety and Alignment
• Evaluation and Benchmarks
• Function Calling and Structured Output
• Generative AI Engineer
• Graph RAG
• Inference Optimization
• Interpretability
• LLM Engineer
• LLM Landscape
• LLMOps
• LLMs Overview
• ML Engineer
• MLOps / LLMOps Engineer
• Model Merging
• Modern Architectures
• Multimodal AI
• RAG Engineer
• RL Alignment
• Reasoning Models
• Role Reference
• Root Overview
• Scaling Laws and Pretraining
• Synthetic Data and Data Engineering
• Tools Overview
• Voice AI

genai-engineer

• Generative AI Engineer

genai-foundations

• Attention Mechanism
• Embeddings
• Tokenization
• Transformers

genai-infra

• Vector Databases

genai-prerequisite

• Deep Learning Fundamentals
• Linear Algebra for AI
• NLP Fundamentals
• Neural Networks
• Probability and Statistics for AI
• Python for AI

genai-safety

• MCP Security

genai-security

• OWASP LLM Top 10

genai-technique

• Structured Outputs

genai-techniques

• AI Agents
• Agent Evaluation
• Fine-Tuning
• Multi-Agent Architectures
• Prompt Engineering
• RAG

governance

• AI Regulation
• Safety and Governance Roles

gpt

• LLMs Overview

gpt-5

• LLM Landscape

gpu

• Deep Learning Fundamentals
• GPU and CUDA Programming

gqa

• Attention Deep Dive
• Modern Architectures

graph-rag

• Graph RAG

graphrag

• Graph RAG

groundedness

• Hallucination Detection

grounding

• Function Calling and Structured Output

grpo

• Advanced Fine-Tuning
• RL Alignment

guardrails

• Guardrails and Content Filtering

hallucination

• Ethics, Safety and Alignment
• Hallucination Detection

humaneval

• Evaluation and Benchmarks

image-generation

• Diffusion Models

images

• Computer Vision Fundamentals

inference

• Distributed Inference and Serving Architecture
• GPU and CUDA Programming
• Inference Optimization
• Model Serving
• Research and Infrastructure Roles

infrastructure

• Cloud ML Services
• Distributed Systems for AI
• ML Experiment and Data Management
• Research and Infrastructure Roles
• Tools Overview

interpretability

• Interpretability

interviews

• System Design for AI Interviews

jailbreak

• Prompt Injection Deep Dive

jailbreaks

• Adversarial ML and AI Security

job-roles

• Role Reference

json-mode

• Function Calling and Structured Output
• Structured Outputs

judges

• LLM Evaluation Deep Dive

kernels

• GPU and CUDA Programming

knowledge-graph

• Graph RAG

knowledge-update

• Continual Learning

kubernetes

• Docker and Kubernetes

kv-cache

• Attention Deep Dive
• Distributed Inference and Serving Architecture
• Inference Optimization

langchain

• Tools Overview

langraph

• Agentic Protocols

language-models

• LLMs Overview

latency

• LLM Routing and Model Selection
• Latency and Throughput Engineering

lifelong-learning

• Continual Learning

lineage

• ML Experiment and Data Management

linear-algebra

• Linear Algebra for AI

linear-attention

• State Space Models

llama

• LLMs Overview

llama-4

• LLM Landscape

llamaindex

• Tools Overview

llm

• Hallucination Detection
• LLMs Overview

llm-as-judge

• LLM Evaluation Deep Dive

llm-comparison

• LLM Landscape

llm-engineer

• LLM Engineer
• Role Reference

llm-internals

• Tokenization

llm-top-10

• OWASP LLM Top 10

llm-training

• Advanced Fine-Tuning

llmops

• AI System Design
• CI/CD for ML
• Cost Optimization
• Data Flywheel Design
• Docker and Kubernetes
• Guardrails and Content Filtering
• LLM Routing and Model Selection
• LLMOps
• Latency and Throughput Engineering
• MLOps / LLMOps Engineer
• Model Serving
• Monitoring and Observability

long-context

• Context Engineering
• Long-Context Engineering

lora

• Fine-Tuning

loss-functions

• Probability and Statistics for AI

machine-learning

• Root Overview

mamba

• State Space Models

matrices

• Linear Algebra for AI

mcp

• Agentic Protocols
• Function Calling and Structured Output
• MCP Security

mech-interp

• Interpretability

memory

• Agent Memory Systems
• GPU and CUDA Programming

mergekit

• Model Merging

methodology

• Research Methodology and Paper Reading

metrics

• Retrieval Evaluation

mha

• Attention Deep Dive

mixture-of-experts

• Modern Architectures

ml-engineer

• ML Engineer

mlflow

• ML Experiment and Data Management

mlops

• CI/CD for ML
• Cloud ML Services
• System Design for AI Interviews

mlops-engineer

• MLOps / LLMOps Engineer

mmlu

• Evaluation and Benchmarks

model-merging

• Model Merging

model-selection

• LLM Landscape
• LLM Routing and Model Selection

moderation

• Guardrails and Content Filtering

moe

• Modern Architectures

monitoring

• LLMOps
• Monitoring and Observability

mqa

• Attention Deep Dive

mrr

• Retrieval Evaluation

multi-agent

• Multi-Agent Architectures

multi-head

• Attention Mechanism

multi-hop-reasoning

• Graph RAG

multimodal

• Computer Vision Fundamentals
• Multimodal AI

natural-language-processing

• NLP Fundamentals

ndcg

• Retrieval Evaluation

needle-in-haystack

• Long-Context Engineering

ner

• NLP Fundamentals

neural-networks

• Neural Networks

nist

• AI Regulation

nlp

• Applied ML and Domain Roles
• NLP Fundamentals

numpy

• Python for AI

o1

• Reasoning Models

o3

• Reasoning Models

observability

• Agent Evaluation
• LLMOps
• Monitoring and Observability

ocr

• Document Parsing and Extraction

open-vs-closed

• LLM Landscape

open-weight

• Model Merging

optimization

• Cost Optimization

optimizer

• Deep Learning Fundamentals

orchestration

• Multi-Agent Architectures

owasp

• OWASP LLM Top 10

papers

• Research Methodology and Paper Reading

pd-disaggregation

• Inference Optimization

pdf

• Document Parsing and Extraction

peft

• Fine-Tuning

perceptron

• Neural Networks

performance

• GPU and CUDA Programming
• Inference Optimization
• Latency and Throughput Engineering

pinecone

• Vector Databases

ppo

• RL Alignment

pre-training

• Scaling Laws and Pretraining

preference-optimization

• RL Alignment

probability

• Probability and Statistics for AI

product

• AI Product Management Fundamentals
• Application and Strategy Roles

production

• AI System Design
• Agent Memory Systems
• Classical ML for GenAI
• Cost Optimization
• Data Flywheel Design
• Docker and Kubernetes
• Document Parsing and Extraction
• Embedding Fine-Tuning
• Guardrails and Content Filtering
• LLM Routing and Model Selection
• LLMOps
• Latency and Throughput Engineering
• Long-Context Engineering
• Model Serving
• Monitoring and Observability
• Prompt Injection Deep Dive

prompt-caching

• Context Engineering

prompt-engineering

• Application and Strategy Roles
• Prompt Engineering

prompt-injection

• Adversarial ML and AI Security
• OWASP LLM Top 10
• Prompt Injection Deep Dive

prompting

• Prompt Engineering

pruning

• Distillation and Compression

pydantic

• Structured Outputs

python

• Python for AI

pytorch

• Python for AI

qdrant

• Vector Databases

qlora

• Fine-Tuning

quantization

• Inference Optimization

queueing

• Latency and Throughput Engineering

queues

• Distributed Systems for AI

radix-attention

• Inference Optimization

rag

• Agent Memory Systems
• Document Parsing and Extraction
• Embedding Fine-Tuning
• Long-Context Engineering
• RAG
• Retrieval Evaluation

rag-engineer

• RAG Engineer
• Role Reference

rag-vs-context

• Context Engineering

ragas

• Evaluation and Benchmarks
• LLM Evaluation Deep Dive

ranking

• Classical ML for GenAI

realtime-api

• Voice AI

reasoning

• Reasoning Models

red-teaming

• Adversarial ML and AI Security
• Prompt Injection Deep Dive
• Safety and Governance Roles

regression

• LLM Evaluation Deep Dive

regularization

• Deep Learning Fundamentals

regulation

• AI Regulation
• Safety and Governance Roles

reliability

• Hallucination Detection

representation

• Embeddings

reproducibility

• Research Methodology and Paper Reading

research

• Distributed Training and Infrastructure
• Research Methodology and Paper Reading
• Research and Infrastructure Roles
• State Space Models

responsible-ai

• AI Regulation
• Ethics, Safety and Alignment

rest

• API Design for AI

retrieval

• Embedding Fine-Tuning
• RAG
• Retrieval Evaluation

reward-model

• RL Alignment

risks

• OWASP LLM Top 10

rlhf

• Ethics, Safety and Alignment
• RL Alignment

rnn

• Neural Networks

rope

• Modern Architectures

routing

• Classical ML for GenAI
• Cost Optimization
• LLM Routing and Model Selection

safety

• Ethics, Safety and Alignment
• Guardrails and Content Filtering
• Safety and Governance Roles

sagemaker

• Cloud ML Services

salary

• Role Reference

sampling

• Probability and Statistics for AI

scaling

• Distributed Inference and Serving Architecture
• Distributed Systems for AI

scaling-laws

• Scaling Laws and Pretraining

schema

• Structured Outputs

search

• Retrieval Evaluation

security

• Adversarial ML and AI Security
• MCP Security
• OWASP LLM Top 10
• Prompt Injection Deep Dive

self-attention

• Attention Mechanism

self-instruct

• Synthetic Data and Data Engineering

sentencepiece

• Tokenization

sentiment

• NLP Fundamentals

sequence-modeling

• State Space Models

serving

• Distributed Inference and Serving Architecture
• Inference Optimization
• Model Serving
• Tools Overview

sglang

• Inference Optimization

similarity

• Embeddings

similarity-search

• Vector Databases

skills

• Role Reference

sklearn

• Classical ML for GenAI

slerp

• Model Merging

sora

• Multimodal AI

sparse-autoencoders

• Interpretability

speculative-decoding

• Inference Optimization

speech-to-text

• Voice AI

ssm

• State Space Models

stable-diffusion

• Diffusion Models

state

• Agent Memory Systems
• Conversational AI

statistics

• Probability and Statistics for AI

strategy

• AI Product Management Fundamentals

streaming

• AI UX Patterns
• API Design for AI

structured-output

• Function Calling and Structured Output
• Structured Outputs

stt

• Voice AI

superposition

• Interpretability

supply-chain

• MCP Security

synthetic-data

• Synthetic Data and Data Engineering

system-design

• AI System Design
• System Design for AI Interviews

teacher-student

• Distillation and Compression

tensor-parallelism

• Distributed Training and Infrastructure

tensors

• Linear Algebra for AI

test-time-compute

• Reasoning Models

testing

• CI/CD for ML
• Evaluation and Benchmarks

text-classification

• NLP Fundamentals

text-to-audio

• Multimodal AI

text-to-speech

• Voice AI

text-to-video

• Multimodal AI

tgi

• Model Serving

thinking

• Reasoning Models

throughput

• Latency and Throughput Engineering

ties

• Model Merging

token-cost

• Cost Optimization

tokenization

• Tokenization

tool-poisoning

• MCP Security

tool-use

• AI Agents
• Function Calling and Structured Output

tools

• Tools Overview

tracing

• Agent Evaluation
• Monitoring and Observability

training

• Deep Learning Fundamentals
• Fine-Tuning
• Scaling Laws and Pretraining

training-data

• Synthetic Data and Data Engineering

training-infrastructure

• Distributed Training and Infrastructure

transformers

• Attention Deep Dive
• Attention Mechanism
• Python for AI
• Transformers

triton

• Model Serving

trl

• Advanced Fine-Tuning

trust

• AI UX Patterns

tts

• Voice AI

ui

• AI UX Patterns

unsloth

• Advanced Fine-Tuning

ux

• AI UX Patterns

vector-db

• RAG
• Tools Overview
• Vector Databases

vector-security

• OWASP LLM Top 10

vectors

• Embeddings
• Linear Algebra for AI

veo

• Multimodal AI

vertex-ai

• Cloud ML Services

vision-language

• Multimodal AI

vit

• Computer Vision Fundamentals

vllm

• Model Serving

voice

• Conversational AI

voice-ai

• Voice AI

wandb

• ML Experiment and Data Management

webhooks

• API Design for AI

whisper

• Voice AI

windsurf

• AI Coding Agents
• Code Generation

wordpiece

• Tokenization

xgboost

• Classical ML for GenAI

zero

• Distributed Training and Infrastructure