AI Engineer
GenAI and ML engineering — DSA, merged ML theory & coding, LLM/agents, SQL, stats, scenarios, analytics concepts, plus craft and product engineering judgment.
This course combines 169 concept guides (Learn library) with 141 practice problems across 10 modules (ML theory + coding are merged so guides are not duplicated). Work each module left to right: study the guides, then drill the problems.
Practice: 0 / 141 solved · ~160h estimated · 169 guides to read
169
64 free · 105 premium in library
141
13 unlocked on your plan · 128 upgrade or preview
10
Modules below (incl. craft / product / analytics)
Premium unlocks every guide and problem in this path. Free tier uses path limits + per-track previews.
Compare plansCurriculum by track
Each module pairs Learn guides with in-app problems where that track has a practice surface (SQL, scenarios, DSA, etc.). Learn-only pillars (craft, product engineering, analytics) are reading-first. Open the Practise arena for the full multi-track dashboard.
Data Structures & Algorithms
Learning: 23 guides (23 free · 0 pro) · Practice: 45 problems (4 unlocked · 41 gated)
- Arrays and Strings: Core Interview Patterns and Execution StrategyFree
- Backtracking: Permutations, Combinations, Subsets & Word SearchFree
- Binary Search Patterns: 3 Templates and Bisect-on-AnswerFree
- Binary Trees & BST: Traversals, LCA, and Classic PatternsFree
- Bit Manipulation: XOR Tricks, Bit Masking & Power-of-Two PatternsFree
- DP on Strings: LCS, Edit Distance, and Regex MatchingFree
- Dynamic Programming: From Recursion to OptimizationFree
- Graph Algorithms: BFS, DFS & Topological SortFree
- Greedy Patterns: Interval Scheduling, Jump Game & Activity SelectionFree
- Heaps & Priority Queues: Top-K, Merge K Lists, and Two-Heap PatternsFree
- How to Approach a DSA Coding InterviewFree
- How to Design a DSA Solution: From Problem to Clean CodeFree
- Interval Patterns: Merge Intervals, Meeting Rooms & Sweep LineFree
- Knapsack DP: 0/1, Unbounded, and Subset Sum VariantsFree
+9 more in the Learn library
- EasyClimbing Stairs
- EasyMaximum Depth of Binary Tree
- EasyReverse Linked List
- EasySingle Number
- EasyTwo Sum
- EasyValid Parentheses
- MediumAccounts Merge
- MediumClone Graph
- MediumCoin Change
- MediumContainer With Most Water
- MediumCourse Schedule (Topological Sort)
- MediumFind All Anagrams in a String
- MediumFind Minimum in Rotated Sorted Array
- MediumGroup Anagrams
- MediumImplement Trie (Prefix Tree)
- MediumJump Game II
- MediumKth Largest Element in an Array
- MediumLinked List Cycle Detection
- MediumLongest Palindromic Subsequence
- MediumLongest Substring Without Repeating Characters
- MediumLowest Common Ancestor of a Binary Search Tree
- MediumLRU Cache
- MediumMeeting Rooms II
- MediumMerge Intervals
- MediumMin Stack
- MediumNetwork Delay Time
- MediumNext Greater Element
- MediumNumber of Connected Components in Undirected Graph
- MediumNumber of Islands
- MediumProduct of Array Except Self
- MediumRotate Image
- MediumSpiral Matrix
- MediumTop K Frequent Elements
- MediumValidate Binary Search Tree
- HardBinary Tree Maximum Path Sum
- HardCheapest Flights Within K Stops
- HardCoin Change II
- HardEdit Distance
- HardLargest Rectangle in Histogram
- HardMedian of Two Sorted Arrays
- HardSerialize and Deserialize Binary Tree
- HardSliding Window Maximum
- HardTrapping Rain Water
- HardWord Break II
- HardWord Search II (Trie + Backtracking)
Machine learning · theory & coding
Learning: 46 guides (12 free · 34 pro) · Practice: 29 problems (3 unlocked · 26 gated)
- Anomaly Detection: Isolation Forest, LOF, ECOD, and ProductionPro
- Attention Mechanisms: From Intuition to Transformer-Scale ReasoningPro
- Bayesian Inference: Priors, Posteriors, MCMC, and Variational InferencePro
- Bias-Variance Tradeoff & ML DebuggingFree
- Bootstrap & Resampling — Uncertainty for Arbitrary StatisticsFree
- Causal Inference: DiD, Instrumental Variables, RDD, and When A/B Tests FailPro
- Computer Vision Fundamentals: CNNs, ResNet, ViT, and Production Transfer LearningFree
- Cross-Validation Strategies: K-Fold, Time Series, Nested CV, and Leakage-Proof PipelinesPro
- DDPM Foundations: ELBO, Score Matching, DDIM, and CFGPro
- Decision Trees: CART, Splitting Criteria, and PruningFree
- Feature Engineering: Leakage-Safe Encoding, Interactions, Temporal, and Production ParityFree
- Graph Neural Networks: Message Passing, GCN, GAT, GraphSAGE & Production GNNsPro
- How to Approach an ML Interview Round at FAANGFree
- How to Structure ML Interview Answers — Derivations and DebuggingPro
+32 more in the Learn library
- EasyImplement k-NN Classifier
- MediumAgent Safety and Guardrails
- MediumBias-Variance Tradeoff Deep Dive
- MediumCompute AUC-ROC from Scratch
- MediumFeature Engineering for Tabular Data
- MediumHuman-in-the-Loop Approval Flow
- MediumImplement AUC-ROC Calculation from Scratch
- MediumImplement Dropout (Training vs Inference)
- MediumImplement K-Means Clustering
- MediumImplement Logistic Regression from Scratch
- MediumImplement Softmax + Cross-Entropy Loss + Gradients
- HardDesign a Multi-Agent Orchestration System
- HardDesign a Persistent Memory System for AI Agents
- HardDesign an Agentic Coding Assistant
- HardDesign an LLM Evaluation & Testing System
- HardImplement a RAG Pipeline
- HardImplement Backpropagation from Scratch
- HardImplement Batch Normalization (Forward + Backward)
- HardImplement Beam Search Decoding
- HardImplement BPE Tokenizer Training
- HardImplement Decision Tree Split (Information Gain)
- HardImplement Gradient Descent Variants
- HardImplement Hierarchical Task Planner
- HardImplement ReAct Loop (Thought/Act/Observe)
- HardImplement Retrieval-Augmented Agent
- HardImplement Scaled Dot-Product Attention
- HardImplement Word2Vec Skip-Gram with Negative Sampling
- HardImplement XGBoost Leaf Weight & Gain
- HardMulti-Agent Debate
GenAI & LLMs
Learning: 39 guides (10 free · 29 pro) · Practice: 7 problems (1 unlocked · 6 gated)
- Chain-of-Thought, Test-Time Compute & Multi-Step ReasoningPro
- Diffusion Models for Images — DDPM, Latent Diffusion, CFG, Stable TrainingPro
- LLM Evaluation & Benchmarking — HELM, MMLU, MT-Bench, Arena, LLM-as-JudgePro
- LLM Fundamentals — Transformers, Attention & ArchitecturePro
- Long-Context LLMs — Lost in the Middle, RAG vs. Natively Long, KV Cache & PackingPro
- Multimodal LLMs — CLIP, Vision-Language Models & Production Vision APIsPro
- Structured Output, Function & Tool Calling — JSON Schema, Strict Mode, Agent SafetyPro
- Tokenization — BPE, WordPiece, SentencePiece & Production ArtifactsFree
- Embeddings — From word2vec to Instruction-Tuned Vectors & Production RAGFree
- Positional Encoding — Sinusoidal, RoPE, ALiBi & Context Length ExtrapolationPro
- Prompt Engineering: From Zero-Shot to Production SystemsFree
- Vector Search for GenAI: HNSW, IVF-PQ, FAISS, and ScaNN in ProductionPro
- Advanced RAG: Hybrid Retrieval, Reranking, and Production ArchitecturePro
- How to Approach a GenAI / LLM System InterviewFree
+25 more in the Learn library
AI Agents
Learning: 39 guides (10 free · 29 pro) · Practice: 0 problems (0 unlocked · 0 gated)
- Chain-of-Thought, Test-Time Compute & Multi-Step ReasoningPro
- Diffusion Models for Images — DDPM, Latent Diffusion, CFG, Stable TrainingPro
- LLM Evaluation & Benchmarking — HELM, MMLU, MT-Bench, Arena, LLM-as-JudgePro
- LLM Fundamentals — Transformers, Attention & ArchitecturePro
- Long-Context LLMs — Lost in the Middle, RAG vs. Natively Long, KV Cache & PackingPro
- Multimodal LLMs — CLIP, Vision-Language Models & Production Vision APIsPro
- Structured Output, Function & Tool Calling — JSON Schema, Strict Mode, Agent SafetyPro
- Tokenization — BPE, WordPiece, SentencePiece & Production ArtifactsFree
- Embeddings — From word2vec to Instruction-Tuned Vectors & Production RAGFree
- Positional Encoding — Sinusoidal, RoPE, ALiBi & Context Length ExtrapolationPro
- Prompt Engineering: From Zero-Shot to Production SystemsFree
- Vector Search for GenAI: HNSW, IVF-PQ, FAISS, and ScaNN in ProductionPro
- Advanced RAG: Hybrid Retrieval, Reranking, and Production ArchitecturePro
- How to Approach a GenAI / LLM System InterviewFree
+25 more in the Learn library
SQL Practice
Learning: 5 guides (2 free · 3 pro) · Practice: 20 problems (2 unlocked · 18 gated)
- SQL Foundations for Data & ML Interviews: JOINs, Aggregations, and Window FunctionsFree
- SQL Indexes and Query Performance: B-Tree, Composite, and Covering IndexesPro
- Subqueries and CTEs: WITH Clauses, Correlated Subqueries, and Recursive PatternsPro
- SQL Query Optimization: Indexes, Query Plans, and Performance at ScalePro
- Window Functions for Analytics: ROW_NUMBER, RANK, LAG/LEAD, and Running TotalsFree
- EasyCustomers Who Never Ordered
- EasyFind and Deduplicate Records
- EasySecond Highest Salary
- MediumAttribution Modeling (Last-Touch vs First-Touch)
- MediumCompute DAU, WAU, MAU Metrics
- MediumCompute Median and Percentiles Without Built-ins
- MediumFunnel Analysis — Checkout Conversion
- MediumPivot — Monthly Revenue by Product Category
- MediumRunning Total and Moving Average
- MediumSelf-Referential Hierarchy (Manager Chain Depth)
- MediumTop N Records Per Group
- HardA/B Test Analysis in SQL
- HardCohort LTV Analysis
- HardExperiment Novelty Effect Analysis
- HardFeature Engineering for ML Models in SQL
- HardLongest Streak of Consecutive Active Days
- HardOrg Chart Traversal with Recursive CTE
- HardQuery Optimization Challenge
- HardUser Retention Cohort Analysis
- HardUser Session Detection with LAG
Scenarios
Learning: 9 guides (3 free · 6 pro) · Practice: 25 problems (2 unlocked · 23 gated)
- How to Approach Data & Product Scenario QuestionsFree
- Scenario Walkthrough: Engagement vs Revenue — Guardrails & HorizonFree
- Scenario Walkthrough: Marketplace Supply–Demand Imbalance — Liquidity FirstPro
- Scenario Walkthrough: Payment Service Returning 500s in ProductionPro
- Scenario Walkthrough: Post-Launch — Was This Feature a Success?Pro
- Scenario Walkthrough: Recommendation Model CTR Dropped 15% OvernightPro
- Scenario Walkthrough: The A/B Test Went Wrong — SRM, Peeking, and InterferencePro
- Scenario Walkthrough: Trust & Safety Escalation — Abuse Signals & ResponsePro
- Scenario Walkthrough: Why Is DAU Dropping?Free
- MediumConvince VP to Fund 6-Month ML Infrastructure Rebuild
- MediumDescribe a System You're Most Proud Of — and What You'd Do Differently
- MediumDesign an A/B Test for a New Ranking Model
- MediumHow Do You Grow From Senior to Staff Engineer?
- MediumHow Would You Define Success Metrics for a New Search Feature?
- MediumLeadership Wants to Know Why Your Model Works — How Do You Explain It?
- MediumOrg Reorg: Your Team Absorbed, Priorities Unclear, Half the Team Leaving
- MediumPartner Team Missed Critical API Deadline — Launch in 2 Weeks
- MediumPrioritize Technical Debt vs. Feature Delivery
- MediumTell Me About a Time You Disagreed With Your Manager
- HardA/B Test Is Positive But a Guardrail Metric Degraded — Do You Ship?
- HardCold-Start Launch: New Country, Zero Historical Data
- HardData Access Conflict: Privacy Team Blocks ML Training Data
- HardDAU Dropped 15% Overnight — Diagnose It
- HardExperiment Trade-Off: Engagement +8%, Retention -3%
- HardFeature Store is Adding 80ms to Real-Time Inference — What Are Your Options?
- HardML Model Accuracy Degraded 8% in Production — What Do You Do?
- HardModel Performs Well Offline (0.92 AUC), Poorly Online (CTR -10%)
- HardP0 at 3am: Payment Service Timing Out
- HardProduction Model Degrading — Rollback or Emergency Retrain?
- HardSilent Data Pipeline Failure — Models Degraded 7 Days Later
- HardStaff-Level Influence: Align 4 Teams Without Formal Authority
- HardWrite a Postmortem for an ML Model That Served Stale Predictions for 6 Hours
- HardYour Experiment Shows Novelty Effect — How Do You Detect and Correct For It?
- HardYour Recommendation Model Has a Fairness Problem
Statistics & A/B Testing
Learning: 7 guides (1 free · 6 pro) · Practice: 15 problems (1 unlocked · 14 gated)
- Statistics & Probability FoundationsPro
- A/B Testing & Experimentation at ScaleFree
- Sequential Testing & the Peeking Problem: Alpha Spending, SPRT, and Always-Valid InferencePro
- Multiple Testing: FWER, FDR, Bonferroni, Holm, and When Each FailsPro
- Bayesian A/B Testing vs Frequentist: Priors, Posteriors, Probability of Superiority, and Expected LossPro
- Practical vs Statistical Significance: MDE, Cohen's d, Confidence Intervals, and Business LossPro
- Non-parametric Statistics: Mann–Whitney U, Kruskal–Wallis & Permutation TestsPro
- MediumBootstrap Confidence Intervals
- MediumHypothesis Testing & Statistical Inference
- MediumImplement Power Analysis & Sample Size Calculation
- MediumMultiple Testing Correction (Bonferroni + Benjamini-Hochberg)
- MediumNovelty Effect Detection (Holdback Analysis)
- MediumProbability Distributions & Statistical Foundations
- HardBayesian Inference & Bayesian A/B Testing
- HardCausal Inference & Observational Studies
- HardDesign a Production A/B Testing Framework
- HardDifference-in-Differences Estimator
- HardHeterogeneous Treatment Effects (CATE)
- HardImplement CUPED Variance Reduction
- HardNetwork Effects & Cluster Randomization
- HardRegression Discontinuity Design (RDD)
- HardSequential Testing & Always-Valid P-Values
Engineering Craft
Learning: 13 guides (3 free · 10 pro) · Learn-first pillar — use Practise arena for cross-track drills
- Data Modeling for Product and Analytics SystemsPro
- Engineering Strategy: Turning Technical Direction into Business OutcomesPro
- How to Approach Craft Interviews: Behavioral, Incident, and Technical CommunicationPro
- How to Be a 10X Engineer: Leverage, Reliability, and Team MultiplicationFree
- Leadership Influence for Engineers: Driving Outcomes Without AuthorityPro
- Mentoring and Growth in Engineering TeamsPro
- Product Metrics & North Star: How Engineers Define and Own SuccessPro
- Staff+ Engineering Interviews: Strategy, Ambiguity, and Org-Level Technical LeadershipPro
- CI/CD Pipelines: Designing Safe, Fast Delivery for ML and SDE SystemsFree
- Data Engineering Pipelines: Reliability, Quality, and EvolutionPro
- STAR Behavioral Interview Stories: Structure, Archetypes, and Leveling SignalsFree
- Backend Engineer Interview Prep PathPro
- Data Scientist Interview Prep PathPro
Production Engineering
Learning: 20 guides (7 free · 13 pro) · Learn-first pillar — use Practise arena for cross-track drills
- Metric Anomaly Triage: Is This a Real Problem or an Instrumentation Bug?Pro
- Kubernetes Operations in Production: Safe Rollouts, Resource Controls, and Cluster GuardrailsPro
- On-Call Incident Response: The First 30 MinutesPro
- SLO Design: Error Budgets, Burn Rate Alerts, and the Reliability TradeoffFree
- Writing the Blameless Postmortem: RCAs That Actually Drive ChangePro
- A/B Test Critique: Finding Flaws in Experiment DesignsPro
- Cloud-Native Production Patterns: Stateless Services, Regions, and Cost-Aware ResiliencePro
- Feature Flags: Safe Rollouts, Kill Switches, and the Dark Launch PatternFree
- Distributed Systems Debugging: Causality, Partial Failures, and Tracing-Driven Root CausePro
- Rewrite vs. Refactor: How to Make the Call Without Destroying the BusinessPro
- AI-Assisted Development and Vibe Coding: Fast Output Without Quality CollapseFree
- Code Review Excellence: The Craft That Most Engineers Never LearnPro
- GitHub End-to-End Workflow: From Issue to Safe Production MergePro
- What Good Code Actually Looks Like: Engineering Craft Beyond the LinterPro
+6 more in the Learn library
Product Analytics
Learning: 7 guides (3 free · 4 pro) · Learn-first pillar — use Practise arena for cross-track drills
- Funnel Analysis: Conversion Optimization, Drop-off Attribution, and Funnel SQLFree
- Product Analytics for Interviews: Metric Design, Root Cause Analysis, and Scenario FrameworksPro
- SQL for Data & ML Interviews: JOINs, Window Functions, and Query OptimizationPro
- Cohort & Retention Analysis: D1/D7/D30 Curves, Churn Interpretation, and Retention SQLFree
- Attribution Modeling: Last-Touch, Multi-Touch, Shapley, MMM, and IncrementalityPro
- User Segmentation & Behavioral Analytics: RFM, Clustering, Personas, and Production GuardrailsPro
- Data Quality Monitoring: Schema Drift, Null Rates, Freshness SLAs, and Anomaly Detection for AnalyticsFree
Finish every module: read the guides, then solve problems in order. Use the global Practise hub for streaks and cross-track progress.