Interview questions

Explain the ReAct Agent Loop

Companies: AMD

AI Agents · Prompt Engineering

Explain Top-k and Top-p Decoding

Companies: Cohere

LLM Inference & Serving

Explain train-test generalization gap

Companies: ByteDance

Explain Train-Test Performance Gap

Companies: ByteDance

Explain Transformer and Fine-Tuning Basics

Companies: Lyft

Fine-Tuning & Alignment Techniques · Transformers & Attention

Explain Transformer and MoE Fundamentals

Companies: Amazon

Transformers & Attention

Explain Transformer Attention Fundamentals

Companies: Adobe

LLM Inference & Serving · Transformers & Attention

Explain Transformer Components and Tree-Ensemble Trade-offs

Companies: Walmart Labs

Explain Transformer Internals and Implement Top-p Decoding

Companies: Mistral AI

ML Coding · Transformers & Attention

Explain Transformer Positional Encoding

Companies: Cadence

Explain unsupervised fraud and evaluation

Companies: PayPal

Explain VAEs, ELBO, KL, and Reparameterization

Companies: Google, Google DeepMind

Explain variance reduction in random forests

Companies: LinkedIn

ML Fundamentals · Supervised Learning

Explain What a Neural Network Is and How It Learns

Companies: Axq Capital

ML Fundamentals · Neural Networks & Training

Explain Why Constant Neural-Network Initialization Fails

Companies: Tower

Explain why LASSO selects features

Companies: Amazon

Explain XGBoost Parallelism Strategies

Companies: Amazon

Supervised Learning

Explain your ML project end-to-end

Companies: Pinterest, Xometry

Explaining Instagram's Recommendation Funnel: Sourcing, Ranking, Signals and Feedback

Companies: Spotify

Ranking Models · Recommendation Systems

Explaining the Main Approaches Recommender Systems Use and When Each One Fits

Companies: Google

Personalization · Recommendation Systems

Extracting Company Names from Noisy Resumes and Web Snippets Context You receive messy resume text (PDF-to-text/OCR, varying casing) and scraped web s...

General practice