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 181–210 of 351 results
- MicrosoftMediumMachine Learning EngineerCalibrate LLM output to match Word formatting
This question tests the ability to design an end-to-end system for enforcing strict structured formatting (e.g., Docx/Markdown) on LLM-generated text, focusing on constraint enforcement and reliability.
ML System DesignOnsiteLLMSystem DesignConstrained Decoding - 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 - 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 EngineerDescribe motivation, ownership, and conflict
This question evaluates motivation, ownership, conflict-resolution, and leadership communication competencies, focusing on interpersonal dynamics and responsibility relevant to a Machine Learning Engineer role.
Behavioral & LeadershipOnsite - MicrosoftMediumMachine Learning EngineerDesign a Product Search System
This question evaluates skills in designing scalable, low-latency product search systems, covering information retrieval, ranking model design, feature generation, data ingestion and indexing pipelines, and serving infrastructure.
ML System DesignOnsite - MicrosoftMediumMachine Learning EngineerDesign a RAG-based assistant service
This question assesses the ability to architect a scalable Retrieval-Augmented Generation (RAG) system, focusing on data indexing, retrieval strategy, and mitigating common LLM issues like hallucinations and safety.
ML System DesignOnsiteRAGLLMVector Databases - MicrosoftMediumMachine Learning EngineerDesign chat and online chess
This problem tests your ability to design a distributed system that supports low-latency, real-time interactions for both chat messaging and synchronized game state for a chess platform.
System DesignOnsiteWebSocketsScalabilityConcurrency - MicrosoftMediumMachine Learning EngineerDesign email ranking and summarization in Outlook
This problem tests the ability to architect a scalable ML pipeline that balances personalized email prioritization with LLM-based summarization while addressing low-latency requirements and data safety.
ML System DesignOnsiteRankingGenerative AISystem Design - MicrosoftMediumMachine Learning EngineerExplain a project deeply
This question assesses the candidate's depth of ownership over a previous machine learning project, specifically testing their ability to articulate system design choices, technical trade-offs, and operational resilience.
Software Engineering FundamentalsOnsiteSystem DesignMLOpsArchitecture - MicrosoftMediumMachine Learning EngineerHandle Cross-Team Dependencies and Scope Conflicts
This question evaluates competency in cross-team collaboration, stakeholder management, conflict resolution, prioritization, and influencing without formal authority in a Machine Learning Engineer context.
Behavioral & LeadershipOnsite - MicrosoftMediumMachine Learning EngineerImplement K-Means and Detect Divisible Subarrays
This question evaluates a candidate's ability to implement an iterative clustering algorithm (K-means) and to reason about subarray sums modulo k, testing competencies in numerical computation, centroid management, edge-case handling, and efficient algorithm design.
Coding & AlgorithmsOnsite - MicrosoftMediumMachine Learning EngineerImplement cache and merge intervals
This question tests the ability to implement a fixed-capacity Least Recently Used (LRU) cache using hash maps and doubly-linked lists, followed by a classic interval processing algorithm to merge overlapping segments.
Coding & AlgorithmsOnsiteLRU CacheIntervalsHash Map - 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 - MolocoadsMediumMachine Learning EngineerCompute the Longest Run of Ones Across Multiple Machines
This problem tests the ability to design a distributed data reduction pattern where partial results can be combined using associative operators to compute a global property.
System DesignOnsiteDistributed SystemsAlgorithmsMapReduce - MolocoadsMediumMachine Learning EngineerFind the Longest Consecutive Run of Ones
Implement an algorithm to find the maximum length of contiguous ones in a binary array without any bit flips, returning 0 for an empty input.
Coding & AlgorithmsOnsitearraystwo-pointerssliding-window - NetflixEasyMachine Learning EngineerDesign an ML Platform Portal
This question assesses the ability to design an internal ML Platform Portal that streamlines the model lifecycle, focusing on experiment tracking, model registry, and workflow automation.
ML System DesignOnsiteMLOpsSystem DesignScalability - NetflixEasyMachine Learning EngineerHow would you support ML stakeholders?
This question evaluates skills in ML infrastructure, stakeholder management, production monitoring, model iteration optimization, and data governance when collaborating with data science partners.
Behavioral & LeadershipOnsite - 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 MLE and Bayesian posterior for Bernoulli
This question evaluates parameter estimation and inferential reasoning for Bernoulli/binomial data, including maximum likelihood estimation and its asymptotic variance, Bayesian updating with a Beta prior and the resulting posterior and posterior predictive probability, as well as interval estimation; it is classified in the Statistics & Math domain. It is commonly asked to assess understanding of frequentist versus Bayesian inference, the behavior and reliability of asymptotic approximations and credible intervals, and the practical implications for predictive probability and uncertainty quantification, testing both conceptual understanding and practical application.
Statistics & MathOnsite - 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 EngineerDesign Duplicate File Detection
This question tests the ability to design a scalable content-based deduplication system using cryptographic hashing and distributed storage principles to manage large-scale file ingestion.
System DesignOnsiteScalabilityDistributed SystemsHashing - OpenAIHardMachine Learning EngineerDesign LLM search handling long token inputs
Design an LLM search and RAG system that handles long documents and long user queries. Covers chunking, hierarchical retrieval, query compression, context budgeting, citations, latency, and evaluation.
ML System DesignOnsite - OpenAIMediumMachine Learning EngineerDesign a Real-Time Sensor Intelligence System
This question evaluates proficiency in end-to-end machine learning system design for real-time sensor-driven products, covering sensor choice trade-offs, data collection and labeling pipelines, model selection and real-time inference, and operational constraints such as latency, reliability, privacy, efficiency, and power.
ML System DesignOnsite
Microsoft
Mistral AI
Netflix
OpenAI