AI & ML Interview Roadmap: A Step-by-Step Study Guide (2025)

# ML/GenAI Research Preparation

## 📐 Math Foundations

### Probability & Distributions
- [Conditional Probability](/core-skills/probability/conditional-probability)
- [Bayes Theorem](/core-skills/probability/bayes-theorem)
- [Permutations & Combinations](/core-skills/probability/permutations-combinations)
- [Bernoulli Distribution](/core-skills/distributions/bernoulli)
- [Binomial Distribution](/core-skills/distributions/binomial)
- [Gaussian (Normal) Distribution](/core-skills/distributions/gaussian)
- [Poisson Distribution](/core-skills/distributions/poisson)
- [Uniform Distribution](/core-skills/distributions/uniform)
- [PDF vs CDF](/core-skills/distributions/pdf-cdf)
- [Mean and Variance](/core-skills/distributions/mean-variance)

### Statistics & Inference
- [Mean, Median, Variance](/core-skills/statistics/descriptive-stats)
- [Law of Large Numbers](/core-skills/statistics/lln)
- [Central Limit Theorem](/core-skills/statistics/clt)
- [MLE (Maximum Likelihood Estimation)](/core-skills/inference/mle)
- [Confidence Intervals (CI)](/core-skills/inference/confidence-intervals)
- [p-value](/core-skills/inference/p-value)
- [z-test](/core-skills/inference/z-test)
- [t-test](/core-skills/inference/t-test)
- [Type I vs Type II Error](/core-skills/inference/type-i-ii-error)
- [A/B Testing](/core-skills/inference/ab-testing)

### Linear Algebra
- [Vectors and Vector Operations](/core-skills/linear-algebra/vectors)
- [Dot Product and Projections](/core-skills/linear-algebra/dot-product)
- [Matrix Multiplication & Transpose](/core-skills/linear-algebra/matrix-multiplication)
- [Identity, Inverse, Rank](/core-skills/linear-algebra/inverse-rank)
- [Linear Dependence and Span](/core-skills/linear-algebra/span-dependence)
- [Eigenvalues and Eigenvectors](/core-skills/linear-algebra/eigenvectors)
- [PCA (Principal Component Analysis)](/core-skills/linear-algebra/pca)
- [SVD (Singular Value Decomposition)](/core-skills/linear-algebra/svd)

### Calculus & Optimization
- [Derivatives and Partial Derivatives](/core-skills/calculus/derivatives)
- [Chain Rule](/core-skills/calculus/chain-rule)
- [Gradient and Jacobian](/core-skills/calculus/gradient)
- [Gradient Descent (GD)](/core-skills/optimization/gradient-descent)
- [Convex vs Non-convex Functions](/core-skills/optimization/convexity)
- [Loss Surfaces and Local Minima](/core-skills/optimization/loss-surfaces)


## 🤖 Machine Learning

### Core Concepts
- [Bias-Variance Tradeoff](/machine-learning/core/bias-variance)
- [Overfitting vs Underfitting](/machine-learning/core/overfitting-underfitting)
- [L1 vs L2 Regularization](/machine-learning/core/regularization)
- [Cross-Validation Techniques](/machine-learning/core/cross-validation)
- [Evaluation Metrics: Accuracy, Precision, Recall, F1, ROC-AUC](/machine-learning/core/evaluation-metrics)

### Linear Models
- [Linear Regression](/machine-learning/linear-models/linear-regression)
- [Logistic Regression](/logistic-regression-interview-guide/)
- [Mean Squared Error (MSE)](/machine-learning/linear-models/mse)
- [Cross-Entropy Loss](/machine-learning/linear-models/cross-entropy)
- [Gradient Descent](/machine-learning/linear-models/gradient-descent)

### Trees & Ensembles
- [Decision Trees: Gini vs Entropy](/machine-learning/trees/decision-trees)
- [Random Forest (Bagging)](/machine-learning/trees/random-forest)
- [Gradient Boosting](/machine-learning/trees/gradient-boosting)
- [XGBoost](/machine-learning/trees/xgboost)

### SVMs & Kernels
- [Hard Margin vs Soft Margin](/machine-learning/svm/hard-soft-margin)
- [Support Vectors & Decision Boundary](/machine-learning/svm/support-vectors)
- [Kernel Trick & Feature Space](/machine-learning/svm/kernel-trick)
- [RBF Kernel](/machine-learning/svm/rbf-kernel)
- [Polynomial Kernel](/machine-learning/svm/polynomial-kernel)

### Feature Engineering
- [Handling Missing Values](/machine-learning/features/missing-values)
- [Normalization (MinMax Scaling)](/machine-learning/features/minmax-scaling)
- [Standardization (Z-score)](/machine-learning/features/z-score-scaling)
- [One-Hot Encoding](/machine-learning/features/one-hot-encoding)
- [Label Encoding](/machine-learning/features/label-encoding)
- [Outlier Detection using Z-score](/machine-learning/features/outliers-zscore)
- [Outlier Detection using IQR](/machine-learning/features/outliers-iqr)

### Unsupervised Learning
- [K-Means Clustering](/machine-learning/unsupervised/kmeans)
- [PCA (Principal Component Analysis)](/machine-learning/unsupervised/pca)
- [PCA: Eigenvectors & Variance Explained](/machine-learning/unsupervised/pca-eigenvectors)

### [Recommendation System](/machine-learning/recommendation-system/)


## 🧠 Deep Learning

### Neural Network Fundamentals
- [Feedforward Neural Networks](/deep-learning/fundamentals/feedforward)
- [Backpropagation](/deep-learning/fundamentals/backpropagation)
- [Gradient Descent in Neural Nets](/deep-learning/fundamentals/gradient-descent)
- [Activation Function: ReLU](/deep-learning/fundamentals/relu)
- [Activation Function: Sigmoid](/deep-learning/fundamentals/sigmoid)
- [Activation Function: Tanh](/deep-learning/fundamentals/tanh)
- [Activation Function: Softmax](/deep-learning/fundamentals/softmax)

### CNNs
- [Convolutional Layers](/deep-learning/cnn/conv-layers)
- [Max Pooling Layer](/deep-learning/cnn/maxpool)
- [Dropout Layer](/deep-learning/cnn/dropout)
- [CNN for Image Classification (CIFAR/MNIST)](/deep-learning/cnn/image-classification)

### RNNs & Transformers
- [Recurrent Neural Networks (RNNs)](/deep-learning/rnn/rnn)
- [LSTM (Long Short-Term Memory)](/deep-learning/rnn/lstm)
- [GRU (Gated Recurrent Unit)](/deep-learning/rnn/gru)
- [Self-Attention Mechanism](/deep-learning/transformers/self-attention)
- [Positional Encoding](/deep-learning/transformers/positional-encoding)
- [Transformer Architecture](/deep-learning/transformers/architecture)
- [BERT (Bidirectional Encoder Representations)](/deep-learning/transformers/bert)
- [Using HuggingFace Transformers](/deep-learning/transformers/huggingface)

### Loss Functions
- [Mean Squared Error (MSE)](/deep-learning/loss-functions/mse)
- [Binary Cross-Entropy](/deep-learning/loss-functions/binary-cross-entropy)
- [Categorical Cross-Entropy](/deep-learning/loss-functions/categorical-cross-entropy)

### Optimization
- [Stochastic Gradient Descent (SGD)](/deep-learning/optimization/sgd)
- [Adam Optimizer](/deep-learning/optimization/adam)
- [Momentum in Optimization](/deep-learning/optimization/momentum)
- [Regularization in Deep Learning](/deep-learning/optimization/regularization)


## 🧮 Coding Interview Prep

### Arrays & Strings
- [Two Sum](/core-skills/coding/arrays/two-sum)
- [Longest Substring Without Repeating Characters](/core-skills/coding/arrays/longest-substring)

### HashMap / Sorting
- [Group Anagrams](/core-skills/coding/hashmap/group-anagrams)
- [Top K Frequent Elements](/core-skills/coding/hashmap/top-k-elements)

### Trees & Graphs
- [Binary Tree Level Order Traversal](/core-skills/coding/trees/level-order-traversal)
- [Binary Tree Inorder Traversal](/core-skills/coding/trees/inorder-traversal)
- [Maximum Depth of Binary Tree](/core-skills/coding/trees/max-depth)
- [Detect Cycle in Directed Graph](/core-skills/coding/graphs/cycle-detection)
- [Topological Sort (Course Schedule)](/core-skills/coding/graphs/topo-sort)

### Sliding Window
- [Minimum Window Substring](/core-skills/coding/sliding-window/min-window)
- [Longest Repeating Character Replacement](/core-skills/coding/sliding-window/repeating-characters)

### Dynamic Programming
- [Coin Change (1D DP)](/core-skills/coding/dp/coin-change)
- [House Robber (1D DP)](/core-skills/coding/dp/house-robber)
- [Maximal Square (2D DP)](/core-skills/coding/dp/max-square)
- [Unique Paths (2D DP)](/core-skills/coding/dp/unique-paths)

### Binary Search / Greedy
- [Search in Rotated Sorted Array](/core-skills/coding/binary-search/rotated-array)
- [Container With Most Water](/core-skills/coding/greedy/container-most-water)

### Linked Lists
- [Reverse Linked List](/core-skills/coding/linked-list/reverse)
- [LRU Cache](/core-skills/coding/linked-list/lru-cache)

### Mock Interviews
- [LeetCode Simulation Guide](/core-skills/coding/mock/simulation-guide)
- [Post-Interview Reflection Notes](/core-skills/coding/mock/reflection-notes)


## 🗃️ SQL + Analytics

### Core SQL Concepts
- [SQL Joins: INNER, LEFT, RIGHT, FULL](/core-skills/sql/core/joins)
- [Filters: WHERE, HAVING](/core-skills/sql/core/filters)
- [GROUP BY and Aggregation](/core-skills/sql/core/group-by-aggregation)

### Window Functions
- [ROW_NUMBER vs RANK](/core-skills/sql/window/row-number-rank)
- [LEAD and LAG](/core-skills/sql/window/lead-lag)

### Advanced Querying
- [Subqueries](/core-skills/sql/advanced/subqueries)
- [Common Table Expressions (CTEs)](/core-skills/sql/advanced/ctes)

### Real-World Data Challenges
- [StrataScratch SQL Practice](/core-skills/sql/practice/stratascratch)
- [LeetCode SQL Interview Questions](/core-skills/sql/practice/leetcode)


## 🧪 ML System Design

### ML Lifecycle
- [ML Lifecycle: Data → Features → Train → Serve → Monitor](/system-design/lifecycle/overview)

### Infrastructure
- [Model Registry](/system-design/infrastructure/model-registry)
- [CI/CD for ML Pipelines](/system-design/infrastructure/ci-cd)
- [Feature Store Design](/system-design/infrastructure/feature-store)

### Monitoring
- [Data Drift](/system-design/monitoring/data-drift)
- [Concept Drift](/system-design/monitoring/concept-drift)

### System Architectures
- [Fraud Detection System](/system-design/architecture/fraud-detection)
- [Recommendation System Pipeline](/system-design/architecture/recommendation)
- [Real-time Ads Ranking System](/system-design/architecture/ads-ranking)

### Design Patterns
- [Batch vs Real-Time Processing](/system-design/patterns/batch-vs-realtime)
- [Latency vs Throughput Trade-offs](/system-design/patterns/latency-throughput)
- [Shadow Deployment vs A/B Testing](/system-design/patterns/shadow-ab-testing)


## 🧬 GenAI & Advanced Topics

### General GenAI

#### Transformers from Scratch
- [Scaled Dot-Product Attention](/generative-ai/transformers/scratch/scaled-attention)
- [Positional Encodings](/generative-ai/transformers/scratch/positional-encoding)
- [Multi-Head Self Attention](/generative-ai/transformers/scratch/multi-head-attention)

#### HuggingFace Applications
- [Sentiment Classification with Transformers](/generative-ai/huggingface/sentiment-classification)
- [Named Entity Recognition (NER)](/generative-ai/huggingface/ner)
- [Question Answering with Transformers](/generative-ai/huggingface/question-answering)

#### GANs
- [Generator vs Discriminator](/generative-ai/gans/generator-discriminator)
- [Mode Collapse](/generative-ai/gans/mode-collapse)
- [Minimax Loss Function](/generative-ai/gans/minimax-loss)

#### Reinforcement Learning
- [Q-Learning Algorithm](/generative-ai/rl/q-learning)
- [SARSA Algorithm](/generative-ai/rl/sarsa)
- [Bellman Equation](/generative-ai/rl/bellman)
- [Deep Q-Network (DQN)](/generative-ai/rl/dqn)
- [Policy vs Value-Based Methods](/generative-ai/rl/policy-vs-value)

### large-language-models

#### Core Concepts
- [LLM Architecture: Encoder, Decoder, Attention](/generative-ai/large-language-models/foundation/architecture)
- [Tokenization: BPE, WordPiece, SentencePiece](/generative-ai/large-language-models/foundation/tokenization)
- [Embeddings: Static vs Contextual](/generative-ai/large-language-models/foundation/embeddings)
- [Language Modeling Objectives: Causal, Masked](/generative-ai/large-language-models/foundation/language-objectives)

#### Training & Fine-Tuning
- [Pretraining vs Finetuning](/generative-ai/large-language-models/training/pretraining-vs-finetuning)
- [Supervised Finetuning (SFT)](/generative-ai/large-language-models/training/supervised-finetuning)
- [Instruction Tuning](/generative-ai/large-language-models/training/instruction-tuning)
- [PEFT: LoRA, Adapters](/generative-ai/large-language-models/training/peft-lora-adapters)
- [Quantization & Distillation](/generative-ai/large-language-models/training/quantization-distillation)

#### Prompting & Reasoning
- [Prompt Engineering Basics](/generative-ai/large-language-models/prompting/prompt-engineering)
- [Chain of Thought (CoT)](/generative-ai/large-language-models/prompting/chain-of-thought)
- [Self-Consistency Decoding](/generative-ai/large-language-models/prompting/self-consistency)
- [Tree of Thoughts (ToT)](/generative-ai/large-language-models/prompting/tree-of-thought)
- [Multimodal Prompting](/generative-ai/large-language-models/prompting/multimodal)

#### Retrieval-Augmented Generation (RAG)
- [RAG Overview](/generative-ai/large-language-models/rag/overview)
- [Embedding Models for RAG](/generative-ai/large-language-models/rag/embeddings)
- [Vector Databases: FAISS, Pinecone, Weaviate](/generative-ai/large-language-models/rag/vector-databases)
- [LangChain for RAG](/generative-ai/large-language-models/rag/langchain)
- [LlamaIndex for RAG](/generative-ai/large-language-models/rag/llamaindex)
- [Serving RAG with FastAPI/Streamlit](/generative-ai/large-language-models/rag/serving)

#### Agents & Autonomy
- [ReAct: Reasoning + Acting](/generative-ai/large-language-models/agents/react)
- [AutoGPT & BabyAGI](/generative-ai/large-language-models/agents/autogpt)
- [Agentic Architectures (Toolformer, Code Interpreter)](/generative-ai/large-language-models/agents/agentic-architectures)
- [Memory, Planning, and Control (MCP)](/generative-ai/large-language-models/agents/mcp)
- [Tool Use, Plugins, APIs](/generative-ai/large-language-models/agents/tool-use)

#### Tooling & Frameworks
- [LangChain Basics](/generative-ai/large-language-models/tools/langchain)
- [LlamaIndex Deep Dive](/generative-ai/large-language-models/tools/llamaindex)
- [HuggingFace Transformers](/generative-ai/large-language-models/tools/huggingface)
- [OpenAI APIs](/generative-ai/large-language-models/tools/openai-api)
- [Model Serving: Triton, VLLM, TGI](/generative-ai/large-language-models/tools/serving)

#### Advanced Architectures & Capabilities
- [GPT Family (GPT-2, 3.5, 4, GPT-4o)](/generative-ai/large-language-models/models/gpt-family)
- [BERT Family (BERT, RoBERTa, DistilBERT)](/generative-ai/large-language-models/models/bert-family)
- [Long-Context Models (Claude, Gemini, Mistral)](/generative-ai/large-language-models/models/long-context)
- [Multimodal large-language-models (GPT-4o, Gemini, MM-ReAct)](/generative-ai/large-language-models/models/multimodal)
- [Open-Source large-language-models (LLaMA, Mistral, Mixtral)](/generative-ai/large-language-models/models/open-source)


## 🧾 Review Tools

### Spaced Repetition
- [Flashcards: Anki Setup](/core-skills/review/tools/anki)
- [Physical Index Card System](/core-skills/review/tools/index-cards)

### Weekly Review
- [How to Create Weekly Review Sheets](/core-skills/review/routines/weekly-review)

### Whiteboard Sketches
- [Decision Tree Splits](/core-skills/review/visuals/decision-trees)
- [PCA 2D Projection from 3D](/core-skills/review/visuals/pca-projection)
- [CNN Architecture Pipeline](/core-skills/review/visuals/cnn-pipeline)

### Summary Sheets
- [Formula Sheet: Bayes Theorem](/core-skills/review/summary/bayes-formula)
- [Formula Sheet: Confidence Intervals](/core-skills/review/summary/confidence-interval)
- [Formula Sheet: Gradients & Optimization](/core-skills/review/summary/gradients)
- [Formula Sheet: PCA Eigenvectors](/core-skills/review/summary/pca-eigenvectors)
- [Formula Sheet: Loss Functions](/core-skills/review/summary/loss-functions)