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 91–120 of 163 results
- MetaHardData ScientistDesign a Restaurant Recommendation System for Food Apps
Meta machine learning system-design prompt on restaurant recommendations for food apps, covering retrieval and ranking models, features, cold start, implicit feedback, offline metrics, A/B testing, and marketplace guardrails.
Machine LearningOnsite - MetaMediumData ScientistDesign an ad recommendation and ranking system
This question evaluates end-to-end ad recommendation and ranking design skills, covering machine learning modeling, recommender systems, causal and counterfactual evaluation, online learning, and production ML engineering within the Machine Learning domain, at a high-level system-design and modeling abstraction.
Machine LearningOnsite - MetaEasyAnalytics EngineerDesign and evaluate an ads ranking algorithm
This problem tests your understanding of the end-to-end machine learning lifecycle for an ads ranking system, focusing on feature engineering, model selection, and the transition from offline metrics to online business impact.
Machine LearningOnsiteAds RankingMetricsEvaluation - MetaHardData ScientistDetect leakage and evaluate a prediction model
This question evaluates competence in production-ready supervised machine learning—detecting and repairing data leakage in logs-based features, designing time-aware cross-validation, defining KPI-driven thresholding and calibration, interpreting model coefficients, and establishing monitoring and retraining policies for a churn prediction model in the Machine Learning domain. It is commonly asked because interviewers need to assess both conceptual understanding of leakage, validation, and calibration principles and practical application skills for deploying and maintaining models with cost-sensitive objectives and monitoring in production, so the level of abstraction spans conceptual reasoning and hands-on practical application.
Machine LearningOnsite - MetaHardData ScientistEvaluate Factors Before Replacing Recommendation Model
Evaluates whether an ads recommendation model should replace an existing production model. Strong answers combine offline validation, online experiments, revenue and advertiser outcomes, user guardrails, conflicting metric interpretation, rollout safety, rollback planning, and executive communication.
Machine LearningOnsite - MetaMediumData ScientistEvaluate Fake-Account Classifier with Precision and Recall Metrics
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 Fake-Account Classifier with Precision and Recall Metrics states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Machine LearningOnsite - MetaMediumData ScientistHow would you predict a car’s turning intention?
This question evaluates applied machine learning skills for vehicle intention prediction, covering temporal sequence modeling versus feature engineering, map- and lane-aware representations, multi-agent interaction reasoning, labeling/time-horizon definition, evaluation metrics and calibration, class imbalance and distribution shift handling, and uncertainty estimation for downstream planning. It is commonly asked because intention prediction is safety-critical in autonomous driving and probes a candidate’s ability to make system-level design trade-offs across data labeling, model architecture, training/validation, and risk-aware evaluation. Category/Domain: Machine Learning; Abstraction level: system-level applied ML for data scientist roles (mid-to-senior).
Machine LearningOnsite - MetaHardData ScientistIdentify Features for Fake News Detection on Facebook
Identify Features for Fake News Detection on Facebook 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 - MetaHardMachine Learning EngineerMachine Learning Fundamentals: Optimizers, Scaling Laws, and Clustering
Tests deep conceptual mastery of modern ML core foundations: AdamW vs. Adam weight decay mechanics, compute-optimal Chinchilla scaling laws, and the mathematical equivalence between Hard Expectation-Maximization in GMMs and k-means clustering.
Machine LearningOnsiteOptimizersScaling LawsClustering - MetaHardData ScientistReplace legacy ads model safely
This question evaluates competence in machine learning systems engineering, including offline validation, counterfactual/off‑policy evaluation, online experimentation design, and production monitoring for ad-ranking models.
Machine LearningOnsite - MetaHardMachine Learning EngineerSelf-Attention: Implementation, Complexity, and Efficient Variants
Tests a candidate's mathematical and practical grasp of scaled dot-product attention, its computational and memory bottlenecks, and modern algorithmic optimizations like FlashAttention and linear attention.
Machine LearningOnsitetransformerattention-mechanismflashattention - MicrosoftMediumData ScientistBuild and Defend a Baseline Model from a CSV
Tests end-to-end applied machine learning design on tabular data: framing the prediction target, eliminating data leakage, establishing a leakage-free validation strategy, selecting baselines and evaluation metrics, and planning deployment monitoring and rollback.
Machine LearningOnsiteModel EvaluationData LeakageMLOps - MicrosoftMediumMachine Learning EngineerClean OCR data and build an LLM dataset
This problem tests the ability to design an automated pipeline for cleaning noisy OCR text output and preparing it for supervised fine-tuning of an LLM.
Machine LearningOnsiteData EngineeringOCRLLM Fine-tuning - MicrosoftHardData ScientistCompare CNN/RNN/LSTM and implement K-means
This question evaluates understanding of deep learning architectures (CNN, RNN, LSTM) and unsupervised clustering implementation (K-means), covering inductive biases, parameter sharing and receptive fields, LSTM gating and vanishing-gradient behavior, tensor shape reasoning, algorithmic complexity, initialization, and cluster handling.
Machine LearningOnsite - MicrosoftMediumMachine Learning EngineerCompare preference alignment methods for LLMs
This question tests your conceptual understanding of alignment techniques, your ability to evaluate trade-offs between stability and performance, and your approach to measuring model safety and utility.
Machine LearningOnsiteRLHFDPOAlignment - MicrosoftMediumMachine Learning EngineerMeasure LLM Quality and Detect Hallucinations, Then Implement an Evaluation Component
A hands-on LLM evaluation exercise on measuring model quality, comparing prompt or model versions, and detecting hallucinations against supplied context. It also asks for a small Python groundedness scorer that flags unsupported sentences and aggregates a hallucination rate, testing evaluation judgment and clean, well-tested code.
Machine LearningOnsite - Mistral AIMediumMachine Learning EngineerAnswer an LLM Systems Quick-Fire Interview
This question tests your breadth of knowledge across the LLM stack, specifically focusing on inference optimization, evaluation strategies, and operational trade-offs.
Machine LearningOnsiteLLMInferenceOptimization - Mistral AIMediumMachine Learning EngineerOptimize Nearest-Center Assignment Without Materializing NxKxD Distances
This problem tests the ability to optimize memory usage in distance computations by leveraging algebraic expansion to avoid creating an intermediate (N, K, D) tensor.
Machine LearningOnsiteNumPyVectorizationLinear Algebra - NetflixMediumData ScientistAddress Fraud Detection with Imbalance and Concept Drift Solutions
Evaluates end-to-end fraud detection ML system design for online payments under drift and imbalance. Strong answers handle delayed labels, class imbalance, feature engineering, cost-sensitive validation, real-time deployment, threshold actions, monitoring, retraining, and concept drift.
Machine LearningOnsite - NetflixHardData ScientistDesign a robust conversion propensity model
This question evaluates a candidate's competency in end-to-end propensity modeling, covering correct labeling to avoid post-treatment leakage, time-windowed feature engineering, class-imbalance and calibration strategies, causal uplift estimation, and production concerns such as monitoring, serving consistency, and cold-start scoring.
Machine LearningOnsite - OpenAIHardMachine Learning EngineerCompute Matrix Prefix Products And Gradients
This question evaluates understanding of automatic differentiation for matrix operations, specifically forward and reverse-mode gradients for sequential, associative (but noncommutative) matrix products, together with algorithmic analysis of time and space complexity.
Machine LearningOnsite - OpenAIMediumMachine Learning EngineerCompute entropy and implement 1-NN
This question evaluates numerical stability and streaming computation for entropy estimation from logits, along with efficient vectorized linear-algebra implementation of 1-nearest-neighbor inference and its interpretation as a neural-network forward pass under different distance metrics.
Machine LearningOnsite - OpenAIMediumMachine Learning EngineerDebug Transformer and Add KV Cache
This problem tests your understanding of transformer architecture by requiring you to fix a broken attention mechanism and implement a Key-Value cache to optimize autoregressive inference.
Machine LearningOnsiteTransformersAttentionInference - OpenAIHardMachine Learning EngineerDebug a Small PyTorch Transformer with Four Bugs, Then Add a KV Cache
Debug a small PyTorch transformer language model that hides four bugs, some of which crash and some of which silently ruin training, then add a key-value cache so generation computes only the newest token each step. It tests causal masking, positional encoding, training-loop order and cached decoding.
Machine LearningOnsite - OpenAIHardMachine Learning EngineerDebug a broken Transformer implementation
This question evaluates a candidate's ability to debug and validate a Transformer implementation, focusing on attention masking, parameter initialization, loss alignment, and other implementation-level correctness issues.
Machine LearningOnsite - OpenAIMediumMachine Learning EngineerDefend a Research Direction and Experiment Design
This question evaluates a candidate's ability to synthesize the state of the art in Machine Learning, defend a research direction, and design rigorous experiments, measuring competencies in literature analysis, methodological justification, experimental design, and technical communication.
Machine LearningOnsite - OpenAIMediumMachine Learning EngineerDerive Sharded Matrix Multiplication and Backpropagation
Derive forward and backward computation for column-sharded matrix multiplication across multiple devices. Track every local tensor shape, identify the collective needed for replicated input gradients, and propose tests for shard ordering, scaling, and numerical errors.
Machine LearningOnsite - OpenAIMediumMachine Learning EngineerFilter Bad Human Annotations
Tests the ability to detect and filter low-quality human labels in large-scale dataset pipelines by modeling annotator reliability, distinguishing genuine ambiguity from noise, and evaluating downstream model performance.
Machine LearningOnsitedata-centric-airlhflatent-variable-models - OpenAIHardMachine Learning EngineerHand-Rolled Backprop: Running Product and Stable Cross-Entropy
Derive and implement, without an autodiff library, the backward pass of a running (cumulative) product in linear time without division, then a numerically stable softmax cross-entropy and its gradient. Tests chain-rule fluency, prefix/suffix tricks, and gradient checking.
Machine LearningOnsiteautodiffbackpropagationnumerical-stability - OpenAIHardMachine Learning EngineerHand-Written Gradients: Prefix-Product Backward Pass and Stable Cross-Entropy
Write gradients by hand: the forward and backward pass of the prefix-product operation, in linear time and without division so inputs may contain zeros, and a numerically stable softmax cross-entropy loss with its gradient in NumPy. It tests the chain rule, prefix and suffix products, and gradient checking.
Machine LearningOnsite
Meta
Microsoft
Mistral AI
Netflix
OpenAI