Machine Learning interview questions

Showing 1–30 of 572 results

• Explain the ReAct Agent LoopMedium

  Explain a ReAct tool loop through state, action selection, observations, recovery, stopping criteria, and validation of task completion.

  AMDSoftware EngineerMachine LearningOnsite
• Explain Transformer Attention FundamentalsHard

  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.

  AdobeMachine Learning EngineerMachine LearningOnsite
• Build a Payment Fraud Detection ModelEasy

  Tests practical machine learning design for payment fraud detection, covering data preprocessing, temporal validation splits, class imbalance handling, and metric selection.

  AdyenMachine Learning EngineerMachine LearningHR Screen
• Build and evaluate an order prediction modelMedium

  This question tests the ability to design a robust end-to-end machine learning pipeline for binary classification, focusing on preventing temporal data leakage, managing class imbalance, and aligning model thresholds with business objectives.

  AirbnbData ScientistMachine LearningTechnical Screen
• Design photo and listing quality modelsMedium

  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.

  AirbnbMachine Learning EngineerMachine LearningOnsite
• Discuss ML Project TradeoffsMedium

  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.

  AirbnbMachine Learning EngineerMachine LearningOnsite
• Build a package-allocation model for couriersHard

  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.

  AmazonData ScientistMachine LearningOnsite
• Choose Between Fine-Tuning and RAG for Client ChatbotHard

  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 Choose Between Fine-Tuning and RAG for Client Chatbot states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.

  AmazonData ScientistMachine LearningTechnical Screen
• Choose Models for Imbalanced Data and Time-Series ForecastingHard

  Choose Models for Imbalanced Data and Time-Series Forecasting 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.

  AmazonData ScientistMachine LearningTechnical Screen
• Choose regularization norms and model formulationsMedium

  This question evaluates understanding of regularization norms (L0, L1, L2, L∞), objective formulations for linear and logistic regression, and practical competencies in handling collinearity, outliers, feature scaling, and optimization difficulty.

  AmazonData ScientistMachine LearningTechnical Screen
• Compare RNNs and Transformers for Long-Sequence Text ClassificationMedium

  Compare RNNs and Transformers for Long-Sequence Text Classification 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.

  AmazonData ScientistMachine LearningTechnical Screen
• Compare Random Forests vs Gradient Boosting rigorouslyHard

  This question evaluates a candidate's ability to choose and configure tree-based models (Random Forest vs. Gradient Boosted Trees), handle high-cardinality categorical features and missingness, mitigate class imbalance and label noise, produce reliable feature importance and calibration, and design an experiment and inference strategy that meets strict latency and resource constraints. It is commonly asked in the Machine Learning domain for Data Scientist roles to assess trade-offs in bias–variance, robustness to correlated features and noise, hyperparameter and encoding decisions, experiment design and evaluation, and tests both conceptual understanding and practical application for production-ready systems.

  AmazonData ScientistMachine LearningTechnical Screen
• Compare Regularization Techniques and Their Use CasesMedium

  Evaluates model evaluation, regularization, and regression basics for predictive analytics. Strong answers define precision and recall, compare L1, L2, L0, and L-infinity penalties, state OLS assumptions, and contrast linear and logistic regression formulas and losses.

  AmazonData ScientistMachine LearningTechnical Screen
• Decide standardization, sparse numerics, correlated featuresMedium

  This question evaluates a candidate's competency in feature engineering and preprocessing for mixed-type tabular data, including handling sparse counts and heavy-tailed monetary features, missingness and zero-inflation, correlated continuous measurements, model-specific scaling needs, and the design of leak-safe pipelines and validation strategies.

  AmazonData ScientistMachine LearningTechnical Screen
• Derive and compare core ML and RL methodsHard

  This question evaluates a candidate's mastery of core machine learning and reinforcement learning concepts, including optimization (gradient methods and batch‑size trade‑offs), supervised versus unsupervised algorithms, policy‑gradient RL and variance reduction, deep RL stability techniques, sequence model complexity (Transformers vs RNNs), embeddings and polysemy, and low‑compute fine‑tuning strategies. It is commonly asked to probe both theoretical understanding and practical engineering judgment about convergence, variance, computational and memory complexity, representation learning, and resource‑constrained model adaptation; the domain is Machine Learning and the assessment spans conceptual understanding and practical application.

  AmazonData ScientistMachine LearningTechnical Screen
• Describe overfitting and L1/L2 regularizationEasy

  This question evaluates understanding of model generalization and regularization techniques by probing knowledge of overfitting and L1/L2 regularization and their effects on model parameters.

  AmazonApplied ScientistMachine LearningTechnical Screen
• Design a Churn Model: Handle Missing Data and JustifyMedium

  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 Design a Churn Model: Handle Missing Data and Justify states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.

  AmazonData ScientistMachine LearningTechnical Screen
• Design a Machine Learning Recommendation System PipelineHard

  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.

  AmazonData ScientistMachine LearningOnsite
• Design a robust traffic forecasting pipelineHard

  This question tests the ability to design an end-to-end, scalable time-series forecasting pipeline, focusing on anomaly handling, structural decomposition, uncertainty quantification, and model validation strategies.

  AmazonData ScientistMachine LearningTechnical Screen
• Design an Automated Home-Price Valuation ModelMedium

  Design an Automated Home-Price Valuation Model 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.

  AmazonData ScientistMachine LearningTechnical Screen
• Design an ML Model for Interview Recommendation PipelineHard

  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.

  AmazonData ScientistMachine LearningOnsite
• Design an end-to-end spam detection systemHard

  This question evaluates a data scientist's system-design and applied machine learning engineering skills—covering problem framing and labeling, feature representation, model selection and calibration, real-time serving constraints, drift detection, and feedback/safety mechanisms—and is commonly asked to probe trade-offs between latency, precision/recall, and robustness against adversarial evolution in production spam detection. Category: Machine Learning; it tests machine learning systems and production-ML competencies at both conceptual-design and practical-application levels, emphasizing calibration, evaluation (offline and online), operational reliability, and rollback/mitigation planning.

  AmazonData ScientistMachine LearningTechnical Screen
• Design and evaluate a RAG systemEasy

  This question evaluates a candidate's competency in designing and evaluating retrieval-augmented generation (RAG) systems, including document ingestion, chunking, embedding and retrieval strategies, reranking, prompt construction, grounding/citation, operational constraints like latency and freshness, permission handling, and evaluation metrics and failure modes. It is commonly asked to assess practical system-design and applied machine learning skills for LLM applications, testing knowledge in the Machine Learning/Information Retrieval domain and requiring both practical application-level reasoning about trade-offs (latency, cost, precision vs. recall) and conceptual understanding of evaluation and guardrails.

  AmazonData ScientistMachine LearningTechnical Screen
• Design end-to-end regression for energy demandHard

  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.

  AmazonData ScientistMachine LearningOnsite
• Design fraud detection across channels with unknownsHard

  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.

  AmazonData ScientistMachine LearningOnsite
• Designing a Bayesian Classifier for Case AnalysisMedium

  Tests your ability to design a probabilistic Bayesian classification system under conditions of informative missingness, non-stationary class priors, and strict calibration requirements.

  AmazonApplied ScientistMachine LearningOnsite
• Diagnose Bias–Variance Trade-off in Supervised LearningMedium

  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.

  AmazonData ScientistMachine LearningOnsite
• Evaluate NLP Classification ModelsEasy

  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.

  AmazonData ScientistMachine LearningOnsite
• Evaluate RAG System Accuracy and Cost Control StrategiesHard

  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 Evaluate RAG System Accuracy and Cost Control Strategies states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.

  AmazonData ScientistMachine LearningTechnical Screen
• Evaluating Generative AI Use and AccuracyMedium

  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.

  AmazonSoftware EngineerMachine LearningOnsite