practice a little every day, paws crossed ♡
Machine Learning Interview Questions
Practice 9403 coding, system design and machine learning questions from 546 companies, sorted by role, topic and interview round. Every question has step-by-step hints, a code runner that supports 8 languages and an AI mentor; members also get the full solution walkthrough.
- 9403
- Questions
- 546
- Companies
- 11
- Topics
- 8
- Languages
Showing 1–30 of 163 results
- AMDMediumSoftware EngineerExplain the ReAct Agent Loop
Explain a ReAct tool loop through state, action selection, observations, recovery, stopping criteria, and validation of task completion.
Machine LearningOnsite - AdobeHardMachine Learning EngineerExplain Transformer Attention Fundamentals
This question tests the candidate's deep conceptual knowledge of the Transformer architecture, focusing on the mathematical mechanics of scaled dot-product attention, memory optimization, and hardware-aware training techniques.
Machine LearningOnsiteTransformersAttentionDeep Learning - AirbnbMediumMachine Learning EngineerDesign photo and listing quality models
This question tests the end-to-end design of a machine learning system to evaluate the quality of listing photos and overall listing attractiveness to improve search ranking and conversion.
Machine LearningOnsiteComputer VisionRanking SystemsFeature Engineering - AirbnbMediumMachine Learning EngineerDiscuss ML Project Tradeoffs
This question evaluates a candidate's skills in model selection, trade-off analysis between precision, recall, latency and infrastructure cost, threshold tuning, reconciliation of offline versus online metrics, and comparative understanding of recommendation models within the Machine Learning domain.
Machine LearningOnsite - AmazonHardData ScientistBuild a package-allocation model for couriers
This question evaluates a candidate's ability to design an end-to-end ML-driven package-to-courier allocation system, testing competencies in predictive modeling (per-stop service-time forecasting), constrained combinatorial optimization for routing and fairness, feature engineering, simulation, and production concerns such as cold-start handling and distribution shift. It is asked to assess how candidates balance competing objectives like on-time delivery versus fairness under real-world constraints (shift hours, vehicle capacity, delivery windows, time-varying travel forecasts), and is categorized under Machine Learning with a focus on practical application-level system design rather than purely conceptual theory.
Machine LearningOnsite - AmazonHardData ScientistDesign a Machine Learning Recommendation System Pipeline
Design a Machine Learning Recommendation System Pipeline evaluates core ML concepts, assumptions, math intuition, training/evaluation trade-offs, and practical failure modes in a realistic interview setting. A strong answer states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Machine LearningOnsite - AmazonHardData ScientistDesign an ML Model for Interview Recommendation Pipeline
Design an ML Model for Interview Recommendation Pipeline evaluates core ML concepts, assumptions, math intuition, training/evaluation trade-offs, and practical failure modes in a realistic interview setting. A strong answer states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Machine LearningOnsite - AmazonHardData ScientistDesign end-to-end regression for energy demand
This question evaluates a candidate's ability to design and justify an end-to-end regression system for next-day site-level energy demand forecasting, testing competencies in time-series modeling, feature engineering, regularization, evaluation metrics and SLAs, production ML pipelines, monitoring, explainability, and data privacy.
Machine LearningOnsite - AmazonHardData ScientistDesign fraud detection across channels with unknowns
This question tests the ability to design an end-to-end fraud detection system that accounts for cold-start problems, cross-channel signals, and the trade-off between customer friction and loss mitigation.
Machine LearningOnsiteFraud DetectionAnomaly DetectionGraph Neural Networks - AmazonMediumApplied ScientistDesigning a Bayesian Classifier for Case Analysis
Tests your ability to design a probabilistic Bayesian classification system under conditions of informative missingness, non-stationary class priors, and strict calibration requirements.
Machine LearningOnsiteBayesian ModelingMissing DataModel Calibration - AmazonMediumData ScientistDiagnose Bias–Variance Trade-off in Supervised Learning
Diagnose Bias–Variance Trade-off in Supervised Learning evaluates core ML concepts, assumptions, math intuition, training/evaluation trade-offs, and practical failure modes in a realistic interview setting. A strong answer states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Machine LearningOnsite - AmazonEasyData ScientistEvaluate NLP Classification Models
This question evaluates competency in NLP classification model evaluation, covering understanding of confusion matrices, precision/recall/F1/AUC metrics, thresholding and trade-offs, handling class imbalance, and connecting metric choices to operational actions and business costs.
Machine LearningOnsite - AmazonMediumSoftware EngineerEvaluating Generative AI Use and Accuracy
Tests a candidate's ability to assess when Generative AI is the right solution, choose appropriate architecture patterns (such as RAG or fine-tuning), and rigorously measure and improve model output accuracy in production.
Machine LearningOnsiteGenerative AIRAGML Evaluation - AmazonHardApplied ScientistExplain Collaborative Filtering Approaches
This question evaluates understanding of collaborative filtering approaches and related competencies such as neighborhood-based versus matrix factorization methods, differences for explicit versus implicit feedback, pointwise versus pairwise loss trade-offs, regularization, cold-start and popularity-bias mitigation, evaluation metrics, and scalability considerations. It is asked in the Machine Learning domain to assess both conceptual understanding and practical application for designing, evaluating (e.g., NDCG, MAP) and scaling recommender systems in technical interviews.
Machine LearningOnsite - AmazonMediumSoftware EngineerExplain Decoder-Only LLM Architecture and How vLLM Serves It Efficiently
A two-part conversational question for AI infrastructure roles: explain how a decoder-only transformer turns a prompt into next-token probabilities, then explain how vLLM serves such models efficiently. It tests transformer internals, KV cache sizing, prefill versus decode bottlenecks, paged KV memory and continuous batching.
Machine LearningOnsite - AmazonMediumApplied ScientistExplain Layer Normalization in Transformers
This question evaluates a candidate's understanding of normalization techniques in deep learning—specifically Layer Normalization in Transformer blocks—covering the LayerNorm equation and the roles of gamma, beta, and epsilon, as well as contrasts with BatchNorm and RMSNorm, in the Machine Learning domain.
Machine LearningOnsite - AmazonHardApplied ScientistExplain Logistic Regression Fundamentals
This question evaluates understanding of logistic regression fundamentals, covering probabilistic modeling, Bernoulli likelihood and logit-link derivation, loss and gradient characterization, calibration and miscalibration remedies, regularization trade-offs, feature scaling and interactions, class imbalance strategies, evaluation metrics for skewed data, coefficient interpretation, and common failure modes. It is commonly asked in technical interviews to assess both theoretical and practical competencies in supervised learning within the Machine Learning domain, with a level of abstraction spanning conceptual derivation and practical application of model behavior and evaluation.
Machine LearningOnsite - AmazonMediumApplied ScientistExplain ML evaluation, sequence models, and optimizers
This question evaluates a candidate's competency in machine learning model evaluation and metrics, sequence modeling trade-offs between transformers and RNNs, image distributional shift detection, and comparative understanding of optimization algorithms within the Machine Learning domain.
Machine LearningOnsite - AmazonHardApplied ScientistExplain NLP/RL concepts used in LLM agents
This question tests the ability to synthesize concepts across LLM agent architecture, RAG systems, and reinforcement learning, focusing on architectural design trade-offs and decision-making logic.
Machine LearningOnsiteLLM-AgentsRAGReinforcement-Learning - AmazonMediumApplied ScientistExplain XGBoost Parallelism Strategies
This question evaluates a candidate's understanding of parallelism and system-level performance in gradient-boosted tree implementations, covering concepts such as histogram-based split finding, sparse feature handling, cache-friendly data layouts, thread-level work partitioning, and multi-machine data-parallel synchronization.
Machine LearningOnsite - AmazonHardApplied ScientistExplain key ML theory and techniques
This interview question evaluates core ML concepts, assumptions, math intuition, training/evaluation trade-offs, and practical failure modes in a realistic interview setting. A strong answer for Explain key ML theory and techniques states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Machine LearningOnsite - AmazonMediumApplied ScientistFrom Early NLP Embeddings to Modern LLM Embeddings
Evaluate the architectural and practical evolution of NLP text embeddings, and formulate a decision framework comparing small bi-encoders versus large LLM-based embedding models based on retrieval quality, latency, and operational cost.
Machine LearningOnsiteEmbeddingsNLPInformation Retrieval - AmazonMediumMachine Learning EngineerGRPO in NumPy: Group-Relative Advantages, Process Rewards and Shaped Rewards
Implement the core of Group Relative Policy Optimization in a NumPy notebook: group-normalized advantages, the clipped objective with a KL penalty, per-token credit from process rewards, and shaped rewards. Tests fluency with array axes and broadcasting and an understanding of how reward normalization interacts with shaping terms.
Machine LearningOnsite - AmazonMediumMachine Learning EngineerImplement Multi-Head Attention with a KV Cache and Cached Grouped-Query Attention
Implement causal multi-head attention from scratch, add a key-value cache for token-by-token decoding, and extend the forward pass to grouped-query attention, where several query heads share one key and value head. Tests tensor shape discipline, masking with cached positions, and reasoning about decode compute and cache memory.
Machine LearningOnsite - AmazonMediumApplied ScientistLLM Fundamentals: Tokenization Design and KL-Regularized SFT
This problem tests your understanding of subword tokenization strategies and the theoretical motivation behind KL-divergence constraints during supervised fine-tuning.
Machine LearningOnsiteLLMTokenizationSFT - AmazonMediumData ScientistOptimize Email Strategy for New Prime Video Series Launch
Evaluates email targeting and ranking strategy for a new Prime Video series launch. Strong answers cover data needs, cold start, ranking models, offline metrics, A/B testing, guardrails, and model selection.
Machine LearningOnsite - AmazonMediumData ScientistOptimize XGBoost for Predicting Marketing Outcomes
Optimize XGBoost for Predicting Marketing Outcomes evaluates core ML concepts, assumptions, math intuition, training/evaluation trade-offs, and practical failure modes in a realistic interview setting. A strong answer states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Machine LearningOnsite - AmazonMediumApplied ScientistTest whether two user populations differ
This question evaluates competency in statistical inference and multivariate analysis, covering hypothesis formulation about equal distributions, preprocessing and normalization considerations, choice of statistical tests or modeling approaches, and interpretation of significance and effect size.
Machine LearningOnsite - AmazonMediumData ScientistWrite and explain gradient descent pseudocode
This question evaluates a candidate's understanding of batch gradient descent for linear regression with an intercept, covering concepts such as mean squared error optimization, vectorized matrix operations, analytical gradient computation, learning rate schedules, stopping criteria, feature scaling, and L2 regularization.
Machine LearningOnsite - AnthropicMediumMachine Learning EngineerBrainstorm How to Keep an AI Model Aligned With Its Intended Goals
Anthropic Fellows final-round practice: a 15-minute open discussion on defining, detecting and training against misalignment and misuse, ending with one falsifiable experiment.
Machine LearningOnsiteAnthropic FellowsAI Safety Fellowshipai-safety
Adobe
Airbnb
Amazon
Anthropic