The AI Interview

Practice Questions

Master AI/ML interview questions from deep learning to system design

365 Questions Available

Linear Regression Using Gradient Descent

Machine LearningEasy

Implement Gradient Descent Variants with MSE Loss

Machine LearningMedium

Implement Adam Optimization Algorithm

Machine LearningMedium

Implement Lasso Regression using ISTA

Machine LearningMedium

Single Neuron

Machine LearningEasy

Sigmoid Activation Function Understanding

Machine LearningEasy

Softmax Activation Function Implementation

Machine LearningEasy

Implementation of Log Softmax Function

Machine LearningEasy

Implement ReLU Activation Function

Machine LearningEasy

Simple Convolutional 2D Layer

Machine LearningMedium

Implementing a Simple RNN

Machine LearningMedium

Poisson Distribution Probability Calculator

Machine LearningEasy

Binomial Distribution Probability

Machine LearningMedium

Normal Distribution PDF Calculator

Machine LearningMedium

Descriptive Statistics Calculator

Machine LearningEasy

Calculate Covariance Matrix

Machine LearningEasy

Generate a Confusion Matrix for Binary Classification

Machine LearningEasy

Calculate Accuracy Score

Machine LearningEasy

Implement Precision Metric

Machine LearningEasy

Implement Recall Metric in Binary Classification

Machine LearningEasy

Implement F-Score Calculation for Binary Classification

Machine LearningEasy

Calculate R-squared for Regression Analysis

Machine LearningEasy

Calculate Mean Absolute Error (MAE)

Machine LearningEasy

Calculate Root Mean Square Error (RMSE)

Machine LearningEasy

Implement K-Fold Cross-Validation

Machine LearningMedium

Calculate Performance Metrics for a Classification Model

Machine LearningMedium

KL Divergence Between Two Normal Distributions

Machine LearningEasy

Principal Component Analysis (PCA) Implementation

Machine LearningMedium

K-Means Clustering

Machine LearningMedium

Linear Regression Using Normal Equation

Machine LearningEasy

Binary Classification with Logistic Regression

Machine LearningEasy

Calculate Jaccard Index for Binary Classification

Machine LearningEasy

Pegasos Kernel SVM Implementation

Machine LearningHard

Implement AdaBoost Fit Method

Machine LearningHard

Matrix-Vector Dot Product

Machine LearningEasy

Transpose of a Matrix

Machine LearningEasy

Dot Product Calculator

Machine LearningEasy

Scalar Multiplication of a Matrix

Machine LearningEasy

Calculate Cosine Similarity Between Vectors

Machine LearningEasy

Calculate Mean by Row or Column

Machine LearningEasy

Calculate Eigenvalues of a Matrix

Machine LearningMedium

Calculate 2x2 Matrix Inverse

Machine LearningEasy

Matrix times Matrix

Machine LearningMedium

Implement Self-Attention Mechanism

Deep LearningMedium

The Pattern Weaver's Code

Deep LearningMedium

Positional Encoding Calculator

Deep LearningHard

Implement Multi-Head Attention

Deep LearningHard

GPT-2 Text Generation

Deep LearningHard

Linear Regression Using Gradient Descent

Deep LearningEasy

Implement Gradient Descent Variants with MSE Loss

Deep LearningMedium

Implement Adam Optimization Algorithm

Deep LearningMedium

Implement Lasso Regression using ISTA

Deep LearningMedium

Softmax Activation Function Implementation

Deep LearningEasy

Implementation of Log Softmax Function

Deep LearningEasy

Sigmoid Activation Function Understanding

Deep LearningEasy

Implement ReLU Activation Function

Deep LearningEasy

Leaky ReLU Activation Function

Deep LearningEasy

Implement the PReLU Activation Function

Deep LearningEasy

Single Neuron

Deep LearningEasy

Implementing a Simple RNN

Deep LearningMedium

Implement Long Short-Term Memory (LSTM) Network

Deep LearningMedium

Simple Convolutional 2D Layer

Deep LearningMedium

Poisson Distribution Probability Calculator

Deep LearningEasy

Binomial Distribution Probability

Deep LearningMedium

Normal Distribution PDF Calculator

Deep LearningMedium

Descriptive Statistics Calculator

Deep LearningEasy

Calculate Covariance Matrix

Deep LearningEasy

Single Neuron with Backpropagation

Deep LearningMedium

Implementing Basic Autograd Operations

Deep LearningMedium

Implement a Simple RNN with Backpropagation Through Time (BPTT)

Deep LearningHard

Matrix-Vector Dot Product

Deep LearningEasy

Transpose of a Matrix

Deep LearningEasy

Dot Product Calculator

Deep LearningEasy

Scalar Multiplication of a Matrix

Deep LearningEasy

Calculate Cosine Similarity Between Vectors

Deep LearningEasy

Calculate Mean by Row or Column

Deep LearningEasy

Calculate Eigenvalues of a Matrix

Deep LearningMedium

Calculate 2x2 Matrix Inverse

Deep LearningEasy

Matrix times Matrix

Deep LearningMedium

Dropout Layer

Data Science Interview PrepMedium

Min-Max Scaling of Feature Values

Data Science Interview PrepEasy

Softmax Activation Function Implementation

Data Science Interview PrepEasy

Single Neuron

Data Science Interview PrepEasy

Implement ReLU Activation Function

Data Science Interview PrepEasy

Calculate F1 Score from Predicted and True Labels

Data Science Interview PrepEasy

Calculate Accuracy Score

Data Science Interview PrepEasy

Calculate Root Mean Square Error (RMSE)

Data Science Interview PrepEasy

Calculate Mean Absolute Error (MAE)

Data Science Interview PrepEasy

Implement Precision Metric

Data Science Interview PrepEasy

Detect Overfitting or Underfitting

Data Science Interview PrepEasy

ExponentialLR Learning Rate Scheduler

Data Science Interview PrepEasy

Linear Regression Using Gradient Descent

Data Science Interview PrepEasy

K-Means Clustering

Data Science Interview PrepMedium

Implement Early Stopping Based on Validation Loss

Data Science Interview PrepEasy

Find the Best Gini-Based Split for a Binary Decision Tree

Data Science Interview PrepMedium

Implement K-Nearest Neighbors

Data Science Interview PrepMedium

One-Hot Encoding of Nominal Values

Data Science Interview PrepEasy

Implement K-Fold Cross-Validation

Data Science Interview PrepMedium

Calculate Mean by Row or Column

Data Science Interview PrepEasy

Feature Scaling Implementation

Data Science Interview PrepEasy

Implement Gradient Descent Variants with MSE Loss

MLE Interview PrepMedium

Compute Multi-class Cross-Entropy Loss

MLE Interview PrepEasy

Implement Ridge Regression Loss Function

MLE Interview PrepEasy

Implement Lasso Regression using ISTA

MLE Interview PrepMedium

Implement Self-Attention Mechanism

MLE Interview PrepMedium

Implement Multi-Head Attention

MLE Interview PrepHard

Positional Encoding Calculator

MLE Interview PrepHard

Single Neuron with Backpropagation

MLE Interview PrepMedium

Implementing a Custom Dense Layer in Python

MLE Interview PrepHard

Implement Batch Normalization for BCHW Input

MLE Interview PrepMedium

Dropout Layer

MLE Interview PrepMedium

Implement ReLU Activation Function

MLE Interview PrepEasy

Softmax Activation Function Implementation

MLE Interview PrepEasy

Implement K-Fold Cross-Validation

MLE Interview PrepMedium

Generate a Confusion Matrix for Binary Classification

MLE Interview PrepEasy

Implement Precision Metric

MLE Interview PrepEasy

Implement Recall Metric in Binary Classification

MLE Interview PrepEasy

Implement F-Score Calculation for Binary Classification

MLE Interview PrepEasy

Calculate AUC (Area Under ROC Curve)

MLE Interview PrepMedium

Implement Adam Optimization Algorithm

MLE Interview PrepMedium

Momentum Optimizer

MLE Interview PrepEasy

Gradient Clipping by Global Norm

MLE Interview PrepMedium

Implement Stratified Train-Test Split

MLE Interview PrepMedium

Implement Grid Search

MLE Interview PrepMedium

Implement Early Stopping Based on Validation Loss

MLE Interview PrepEasy

Feature Drift Detection using Population Stability Index

MLE Interview PrepMedium

A/B Test Statistical Analysis for Model Comparison

MLE Interview PrepHard

Calculate P50/P95/P99 Latency Percentiles

MLE Interview PrepEasy

Implement INT8 Quantization

MLE Interview PrepMedium

Implement Prediction Distribution Monitoring

MLE Interview PrepMedium

Calculate Statistical Power for Experiment Design

MLE Interview PrepMedium

Implement Request Batching for Inference

MLE Interview PrepMedium

Simple Convolutional 2D Layer

MLE Interview PrepMedium

Implement Global Average Pooling

MLE Interview PrepEasy

Implement Long Short-Term Memory (LSTM) Network

MLE Interview PrepMedium

Implement GRU Cell

MLE Interview PrepMedium

Linear Regression Using Gradient Descent

MLE Interview PrepEasy

Train Logistic Regression with Gradient Descent

MLE Interview PrepHard

K-Means Clustering

MLE Interview PrepMedium

Principal Component Analysis (PCA) Implementation

MLE Interview PrepMedium

Decision Tree Learning

MLE Interview PrepHard

Calculate Image Brightness

Computer VisionEasy

Grayscale Image Contrast Calculator

Computer VisionEasy

Optical Flow EPE with Masks (OmniWorld-style metric)

Computer VisionMedium

PCA Color Augmentation

Computer VisionHard

Convert RGB Image to Grayscale

Computer VisionEasy

Flip an Image Horizontally or Vertically

Computer VisionEasy

Apply Zero Padding to an Image

Computer VisionEasy

Bilinear Image Resizing

Computer VisionMedium

Sobel Edge Detection

Computer VisionMedium

Non-Maximum Suppression for Object Detection

Computer VisionHard

MMLU Log-Probability Scoring

Rubric-Based LLM Judge Evaluation

Boxed Answer Extraction for Math Benchmarks

Math Answer Verification with Equivalence Checking

Pairwise Preference Judge for LLM Comparison

Code Execution Verifier for Programming Benchmarks

Direct Preference Optimization (DPO) Loss

Top-p (Nucleus) Sampling

What are Large Language Models (LLMs)?

Tokenization

Hallucination in LLMs

Temperature Parameter

Prompt Engineering

Fine-Tuning

Generative vs Discriminative AI

Pre-training

Zero-Shot Prompting

Context Window

Transformer Architecture

Self-Attention Mechanism

Encoder vs Decoder

Retrieval-Augmented Generation (RAG)

Vector Databases

Embeddings

RLHF

Top-K vs Top-P Sampling

Cross-Entropy Loss

LoRA (Low-Rank Adaptation)

Perplexity

Few-Shot Prompting

Greedy vs Beam Search

Semantic Search

Softmax Function

Masked Language Modeling

Instruction Tuning

Gradient Descent in LLMs

Overfitting vs Underfitting

Transfer Learning

FlashAttention

Rotary Position Embeddings (RoPE)

KV Cache

Mixture of Experts (MoE)

Direct Preference Optimization (DPO)

Quantization (GPTQ / AWQ)

Speculative Decoding

PagedAttention

Tensor Parallelism vs Pipeline Parallelism

Grouped-Query Attention (GQA)

Contrastive Decoding

Catastrophic Forgetting

ALiBi Positional Encoding

Chinchilla Scaling Laws

Self-Supervised Learning Frameworks

The Softmax Bottleneck

Constitutional AI

Length Extrapolation Limitation

Byte-Pair Encoding (BPE)

Catastrophic Forgetting in RLHF

Build a Simple ETL Pipeline (MLOps)

Calculate Model Inference Statistics for Monitoring

Calculate Batch Prediction Health Metrics

Calculate SLA Compliance Metrics for Model Service

Analyze Canary Deployment Health for Model Rollout

Data Quality Scoring for ML Pipelines

Feature Drift Detection using Population Stability Index

A/B Test Statistical Analysis for Model Comparison

ML Pipeline DAG Scheduler with Critical Path Analysis

Implement Prediction Distribution Monitoring

Implement Request Batching for Inference

Implement Volume Bars Sampling

Reinforcement LearningMedium

Implement Dollar Bars Sampling

Reinforcement LearningMedium

Diffusion Reconstruction Loss

Reinforcement LearningMedium

Forward Diffusion Process

Reinforcement LearningMedium

Forward & Backward Diffusion Process

Reinforcement LearningMedium

Implement the GRPO Objective Function

Reinforcement LearningHard

Policy Gradient with REINFORCE

Reinforcement LearningHard

Implement Q-Learning Algorithm for MDPs

Reinforcement LearningMedium

Gridworld Policy Evaluation

Reinforcement LearningMedium

Implement the Bellman Equation for Value Iteration

Reinforcement LearningMedium

Epsilon-Greedy Action Selection for n-Armed Bandit

Reinforcement LearningMedium

Incremental Mean for Online Reward Estimation

Reinforcement LearningEasy

Exponential Weighted Average of Rewards

Reinforcement LearningEasy

Upper Confidence Bound (UCB) Action Selection

Reinforcement LearningEasy

Gradient Bandit Action Selection

Reinforcement LearningMedium

Gambler's Problem: Value Iteration

Reinforcement LearningHard

Compute Discounted Return

Reinforcement LearningEasy

Evaluate Expected Value in a Markov Decision Process

Reinforcement LearningMedium

Calculate the Discounted Return for a Given Trajectory

Reinforcement LearningEasy

Monte Carlo Tree Search

Reinforcement LearningHard

GSPO: Group Sequence Policy Optimization

Reinforcement LearningHard

Dr. GRPO: Complete Objective Function

Reinforcement LearningMedium

Group Relative Advantage for GRPO

Reinforcement LearningEasy

KL Divergence Estimator for GRPO

Reinforcement LearningEasy

Pass@k and Majority Voting Evaluation Metrics

Reinforcement LearningEasy

Budget-Constrained RL Loss

Reinforcement LearningMedium

Compute Temporal Difference Error

Reinforcement LearningEasy

First-Visit Monte Carlo Prediction

Reinforcement LearningMedium

n-Step TD Prediction

Reinforcement LearningMedium

TD(llama) with Eligibility Traces

Reinforcement LearningHard

Fine-Tune Model Weights with RLHF Policy Gradient

Reinforcement LearningMedium

RAFT: Iterative Reward-Ranked Fine-Tuning Loop

Reinforcement LearningMedium

Byte Pair Encoding (BPE) Tokenizer

Optimal String Alignment Distance

Implement TF-IDF (Term Frequency-Inverse Document Frequency)

GPT-2 Text Generation

BM25 Ranking

Evaluate Translation Quality with METEOR Score

Compute Pointwise Mutual Information

Calculate Unigram Probability from Corpus

Calculate Perplexity for Language Models

BLEU Score for Text Generation

Bradley-Terry Model for Pairwise Rankings

Exact Match Score with Normalization

MMLU Letter-Matching Evaluation

ReAct Pattern Implementation

Function Call Parser

Sliding Window Memory Buffer

Basic Agent Loop with Termination

Sequential Prompt Chain

Keyword-Based Tool Selector

Tool Execution with Try-Catch

Observation-Action Cycle Logger

Token Budget Tracker

Simple Self-Critique Wrapper

Idempotency Key Generator

Tool Input Validator

Agent State Machine

Simple Input Guardrail

Deterministic vs Non-Deterministic Classifier

Simple Knowledge Graph Memory

Factuality Checker for Agent Outputs

Tool Misuse Detector

Blackboard Knowledge System

Parallel Agent Executor

Conversation Memory Compressor

Agent Message Bus

Circuit Breaker for Tool Calls

Agent Evaluation Framework

Tool Execution Sandbox

Loop Detection and Prevention

LRU-K Memory Eviction

Reward Hacking Detector

Hierarchical Task Decomposer

Coordinator Agent Implementation

Role-Based Agent System

Multi-Layer Guardrail System

Agent Observability Logger

Agent Failure Recovery System

Safety Constraint Validator

Design Production-Ready Agent System

Distributed Multi-Agent Coordinator

Agent Latency Optimizer

Agent Cost Optimizer

Scalable Multi-Agent Orchestrator

Advanced Failure Recovery with Checkpointing

End-to-End Observability Pipeline

Tree of Thoughts Implementation

Hierarchical Memory System

Hierarchical Task Network Planner

Tool Composition and Chaining Engine

Constitutional AI Safety Layer

Agent Self-Improvement System

Multi-Agent Consensus Protocol

Advanced RAG with Query Rewriting and Fusion

Define and Implement a Basic AI Agent Class

Implement Agent Lifecycle States

Build a Prompt Chain Pipeline

Implement Short-Term vs Long-Term Memory

Implement the ReAct Pattern

Agent Self-Reflection and Self-Critique

Basic Tool Registration and Calling

Implement Termination Conditions for Agent Loops

Observation-Thought-Action Cycle Implementation

Implement Basic Guardrails for Agent Output

Vector Database Integration for Agent Memory

Implement Tool Retry Mechanism

Agent Token Budget Controller

Implement Role-Based Multi-Agent System

Implement Basic Hallucination Detection

Implement a Full ReAct Agent with Dynamic Tool Selection

Planner-Executor Agent Architecture

Implement RAG Inside an Agent

Implement Agent Communication Protocol

Task Decomposition with Dependency Resolution

Implement Episodic Memory with Retrieval

Implement Tool Idempotency and Validation

Debate Agent Implementation

Implement Agent Sandboxing and Safety Constraints

Memory Compression and Summarization

Implement Coordinator Agent Pattern

Knowledge Graph Integration for Agent Reasoning

Implement Agent Evaluation Framework

Implement Parallel Agent Execution

Implement Hierarchical Agent System

Blackboard Architecture for Multi-Agent Coordination

Design a Production-Ready AI Agent System

Design a Distributed Multi-Agent System with Fault Tolerance

Implement Agent Observability and Distributed Tracing

Latency Optimization for Multi-Step Agent Pipelines

Implement Agent Cost Optimization System

Implement Failure Recovery and Checkpoint System

Design an Agent with Full Conflict Resolution

Implement Tool Misuse Detection System

Implement Agent Alignment and Value Alignment Checker

Implement Scalable Multi-Agent Message Router

Implement Semantic Memory Eviction with Relevance Scoring

Deterministic vs Non-Deterministic Tool Usage

Tool Execution Loop with Configurable Error Policies

Tree of Thoughts Planning Agent

Generator-Critic Self-Play Loop

Full Agent Observability Pipeline with Cost Tracking and Alerts

Auto-Scaling Agent Worker Pool

Cross-Session Agent Memory and User Profiling

Adaptive Instruction Priority and Conflict Resolution