Topological Sort: Kahn’s Algorithm and DFS Approach
Topological sort is the graph algorithm you need for scheduling problems: course prerequisites, build systems, task dependencies, and package managers. […]
Graphs
Graphs
Number of Islands: Flood Fill Pattern Explained
Number of Islands (LeetCode 200) is the most common entry-level graph problem in technical interviews. It appears at Google, Amazon,
Graphs
Detect a Cycle in a Graph: Directed and Undirected
Cycle detection is asked in interviews at Google, Meta, Amazon, and anywhere that tests graphs. The classic application is deadlock
Graphs
BFS vs DFS: When to Use Each with Examples
BFS and DFS are the two foundational graph traversal algorithms. Every other graph algorithm — Dijkstra, Bellman-Ford, topological sort, cycle
AI/ML Interview Questions
AI Ethics and Fairness: Interview Questions and Technical Framework
AI ethics and fairness questions appear in interviews at every major tech company — and not just for policy roles.
AI/ML Interview Questions
How to Evaluate an LLM: Benchmarks, Human Eval, and Red-Teaming
“How do you evaluate an LLM?” is now a standard interview question at companies building AI products. It tests whether
AI/ML Interview Questions
MLOps Interview Questions: Pipelines, Monitoring, and Deployment
MLOps interviews test whether you can build and maintain ML systems in production — not just train models in notebooks.
AI/ML Interview Questions
ML System Design: Build a Search Ranking System
Search ranking is one of the most technically demanding ML system design problems. It combines information retrieval, multi-stage ranking, real-time
AI/ML Interview Questions
ML System Design: Build a Fraud Detection System
Fraud detection is one of the highest-stakes ML applications — a false negative costs money, a false positive costs a
AI/ML Interview Questions
ML System Design: Build a Spam Classifier
“Design a spam classifier” is one of the most common ML system design questions at Google, Meta, and Microsoft. Unlike
AI/ML Interview Questions
How to Detect Model Drift in Production
Model drift is one of the most common production ML failure modes — and one of the most underestimated in
AI/ML Interview Questions
NLP Interview Questions: Tokenization, Embeddings, and BERT
NLP interview questions appear across ML engineer, data scientist, and applied researcher roles at companies like Google, Meta, OpenAI, and
AI/ML Interview Questions
Computer Vision Interview Questions: CNNs, Object Detection, and Transfer Learning
Computer vision is one of the most interview-tested areas of ML, especially at companies with physical products, autonomous systems, or
AI/ML Interview Questions
How Does RLHF Work? Reinforcement Learning from Human Feedback Explained
RLHF (Reinforcement Learning from Human Feedback) is the technique that transforms a raw language model into an assistant — the
System Design
Design an LLM Inference API
Design an LLM inference API — the service that accepts user prompts and returns model completions, like the OpenAI API,