practice a little every day, paws crossed ♡
Machine Learning Engineer 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 481–510 of 782 results
- 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 - OpenAIMediumMachine Learning EngineerImplement 1NN with NumPy
Tests your ability to implement a fast, vectorized 1-Nearest Neighbor (1NN) classifier using NumPy, focusing on memory-efficient distance computations and tie-breaking.
Machine LearningTechnical Screennumpyvectorizationmachine-learning - OpenAIMediumMachine Learning EngineerImplement Masked Cross-Entropy with Label Smoothing
Implement a numerically stable, masked cross-entropy loss function with label smoothing and temperature scaling in NumPy, returning both the loss and analytical gradients.
Machine LearningTechnical Screenmachine-learningnumpydeep-learning - OpenAIMediumMachine Learning EngineerImplement Prefix Products and Their Backward Pass
Work through inclusive prefix products in separate-output, in-place, reverse-gradient, and parallel variants. Explain zeros, overflow, mutation and aliasing, constant temporary workspace, synchronization, floating-point effects, and the work/depth trade-offs of each part.
Machine LearningOnsite - OpenAIHardMachine Learning EngineerImplement a 1-Nearest-Neighbor Classifier with a Manhattan-Distance Follow-Up
Implement a 1-nearest-neighbor classifier that labels each query point with the label of its closest training point under Euclidean distance, then extend it to Manhattan distance. Tests vectorized distance computation under memory limits, tie handling and how the choice of metric changes predictions.
Machine LearningTechnical Screen - OpenAIHardMachine Learning EngineerImplement in-memory database insert and delete operations
This question evaluates understanding of data structures and algorithmic complexity in the context of designing a key-value in-memory database, and it falls under the Coding & Algorithms domain for a Machine Learning Engineer role while focusing on practical implementation skills.
Coding & AlgorithmsOnsite - OpenAIMediumMachine Learning EngineerImplement vectorized NumPy ops and explain broadcasting
This question evaluates proficiency in vectorized numerical computing with NumPy, understanding of broadcasting semantics, and awareness of numerical stability and algorithmic time/space complexity when manipulating high-dimensional arrays.
Data Manipulation (SQL/Python)Onsite - OpenAIHardMachine Learning EngineerImprove Training With Noisy Annotators
This question evaluates a candidate's ability to handle label noise by estimating annotator reliability and applying data-cleaning, relabeling, or reweighting methods while measuring model performance and understanding classification metrics.
Machine LearningOnsite - OpenAIHardMachine Learning EngineerImprove classifier with noisy multi-annotator labels
This question evaluates a candidate's ability to analyze noisy multi-annotator labels, design label-aggregation and dataset-splitting strategies, and choose modeling and evaluation approaches for binary text classification.
Machine LearningTechnical Screen - OpenAIMediumMachine Learning EngineerInfer Generic Return Types
Implement a toy type-inference engine that unifies generic parameter types with concrete argument types and substitutes resolved type variables to determine the return type.
Coding & AlgorithmsOnsiterecursiontreetype-systems - OpenAIMediumMachine Learning EngineerMaintain Entropy for a Streaming Distribution
Maintain empirical Shannon entropy after every categorical observation without rescanning all categories. The discussion should cover arbitrary identifiers, first-item behavior, exact counts, floating-point drift, concurrency, deletions, sliding windows, and merging summaries from separate stream partitions.
Statistics & MathOnsite - OpenAIMediumMachine Learning EngineerModel Infection, Immunity, Delayed Death, and Burn Interventions on a Grid
Design and implement a discrete grid simulation modeling a five-stage disease progression with state countdowns, immunity, delayed mortality, and external burn interventions.
Software Engineering FundamentalsTechnical Screensimulationmatrixstate-machine - OpenAIHardMachine Learning EngineerRepair a Broken Tiny Language Model, Then Make Decoding Incremental
Find four planted bugs in a compact PyTorch decoder-only language model (some produce NaNs, some silently ruin learning), then add key/value caching so generation processes one new token per step.
Machine LearningOnsitepytorchtransformersdebugging - OpenAIHardMachine Learning EngineerSchedule Incremental Labeling Tasks
This problem tests the ability to design an incremental task scheduler that balances workload across a pool of annotators while maintaining fairness and deterministic state transitions.
Coding & AlgorithmsOnsiteHeapsSchedulingGreedy - OpenAIHardMachine Learning EngineerSearch Monster Battle Strategies
Design a search algorithm using state-space exploration to find the minimum number of turns required to defeat a boss given transient health, scripted boss attacks, and a single-use revive.
Coding & AlgorithmsOnsiteBreadth-First SearchState Space SearchGraph Algorithms - OpenAIHardMachine Learning EngineerSelect high-quality math documents from crawls
This question assesses the ability to design a scalable pipeline that ingests, cleans, extracts, and filters high-quality mathematical content from diverse, noisy web-crawled sources.
ML System DesignOnsiteSystem DesignNLPData Engineering - OpenAIHardMachine Learning EngineerSimulate Infection Spread on a Grid
Implement a discrete-time cellular automaton simulating epidemic spread on a 2D grid with multi-day infection states, immunity waning, and mortality rules.
Coding & AlgorithmsTechnical ScreenSimulationMatrixCellular Automata - OpenAIMediumMachine Learning EngineerSimulate Infection Spread with Immunity and Recovery
Implement a cellular automaton simulation modeling disease spread on a 2D grid with discrete cell states and timed recovery.
Coding & AlgorithmsTechnical ScreenGrid SimulationCellular AutomataBFS - OpenAIHardMachine Learning EngineerSimulate Plant Infection With Controlled Burning
This question evaluates a candidate's ability to implement discrete-time grid simulations with delayed state transitions, reason about simultaneous updates and neighborhood effects, and perform a limited combinatorial optimization (choosing one row or column) to minimize a global outcome.
Coding & AlgorithmsOnsite - OpenAIMediumMachine Learning EngineerSimulate Turn-Based Monster Battles
This problem tests your ability to design a stateful simulation engine that handles turn-based mechanics, complex status modifiers, and dynamic combat interactions.
Coding & AlgorithmsOnsiteSimulationState ManagementGame Logic - OpenAIHardMachine Learning EngineerStreaming Entropy with Numerical Stability
Implement an online, numerically stable algorithm to compute Shannon entropy over an unbounded stream of categorical tokens with O(1) updates.
Coding & AlgorithmsTechnical Screenstreamingmathnumerical-computing - OpenAIMediumMachine Learning EngineerTrack Expiring GPU Credits
Design an in-memory credit ledger to track expiring GPU compute credits, support priority consumption, and manage resource debt.
Coding & AlgorithmsOnsiteHeapDesignGreedy - OpenAIHardMachine Learning EngineerTrain a classifier and analyze dataset
This question evaluates proficiency in end-to-end supervised machine learning workflows—covering data validation, exploratory data analysis, preprocessing, model training and selection, evaluation metrics and calibration, fairness assessments, and reproducibility—and tests competencies in applied machine learning engineering, statistical reasoning, and model governance within the Machine Learning domain. It is commonly asked in technical interviews because it verifies practical implementation skills and judgment for deploying reliable classifiers, aligning metrics to business goals and diagnosing performance and fairness across slices, with emphasis on practical application informed by conceptual understanding.
Machine LearningTechnical Screen - OpenAIMediumMachine Learning EngineerTrain and analyze a classifier
This question evaluates proficiency in end-to-end machine learning engineering, including exploratory data analysis, time-aware train/validation/test splitting, model baseline and improvement, class imbalance strategies, leakage-safe hyperparameter tuning, metric computation and calibration, error analysis, reproducible training pipelines with CLI/config/seed control, explainability (feature importance/SHAP and ablations), and documentation of risks, fairness checks and monitoring hooks. It is commonly asked to assess practical ability to manage the full ML lifecycle and data hygiene in production-like scenarios, testing applied Data Manipulation (SQL/Python) and Machine Learning competencies with an emphasis on practical application while also requiring conceptual understanding of evaluation, calibration and fairness.
Data Manipulation (SQL/Python)Technical Screen - OpenAIMediumMachine Learning EngineerVectorize One-Nearest-Neighbor and Express It as a Neural Forward Pass
Tests vectorized distance computation in array libraries and the mathematical equivalence between nearest-prototype classification and an affine neural network layer.
Machine LearningTechnical Screenvectorizationnearest-neighborslinear-algebra - OtherMediumMachine Learning EngineerImplement Linear Regression Training
This question evaluates understanding of linear regression, mean squared error loss, gradient computation, parameter updates, and proficiency with vectorized numerical operations used in batch gradient descent.
Coding & AlgorithmsOnsite - PDT PartnersMediumMachine Learning EngineerList All Positive Divisors of an Integer in Ascending Order, Then Beat Square-Root Time
Given a positive integer up to one trillion, return every positive divisor in ascending order, each listed once. The task tests divisor enumeration, correct handling of perfect squares and 64-bit values, and a follow-up asking whether the running time can grow more slowly than the square root of n.
Coding & AlgorithmsTechnical Screen - PDT PartnersMediumMachine Learning EngineerProject Deep Dive: Low-Latency LSTM Inference at Scale and the LSTM vs Transformer Choice
A project deep dive on a small LSTM model served for large-scale, latency-sensitive inference. The candidate must explain the deployment hardware, latency requirement and use case, how inference latency was reduced, why an LSTM was chosen over a Transformer, and whether that choice still holds today.
Machine LearningTechnical Screen - PayPalHardMachine Learning EngineerDesign a traditional fraud detection system
This question evaluates a Machine Learning Engineer's competency in end-to-end ML system design for real-time payments fraud detection, including labeling under delayed confirmations, handling extreme class imbalance and sampling, feature engineering across behavioral, graph, device and merchant signals, model selection for latency and scale, and production scoring and monitoring architecture. It is commonly asked in the ML System Design category to assess how an engineer balances low-latency decision-making with delayed sparse labels, calibration and threshold trade-offs, operational scalability and resiliency, and drift/adversarial detection, testing both conceptual understanding and practical application.
ML System DesignOnsite - PayPalMediumMachine Learning EngineerMaximize ones with limited flips
This question evaluates proficiency with array algorithms, particularly sliding-window and two-pointer reasoning, complexity analysis, and the ability to adapt solutions for streaming data.
Coding & AlgorithmsOnsite
OpenAI
PayPal