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 181–210 of 348 results
- Mistral AIMediumSoftware EngineerCompare Reward-Model RLHF and Direct Preference Optimization
Compare reward-model RLHF and DPO through preference data, policy objectives, reference regularization, training stages, and evaluation under distribution shift.
Machine LearningTechnical Screen - Mistral AIMediumSoftware EngineerCompare Tensor Parallelism and Pipeline Parallelism
Compare transformer tensor and pipeline parallelism through parameter partitioning, collectives, activation transfers, microbatch bubbles, memory, and inference latency.
Machine LearningTechnical Screen - Mistral AIMediumSoftware EngineerExplain Adam, AdamW, and Decoupled Weight Decay
Understand Adam moment estimates and bias correction, then compare gradient-based L2 regularization with AdamW’s decoupled weight decay and learning-rate interaction.
Machine LearningTechnical Screen - Mistral AIMediumSoftware EngineerExplain Mixture of Experts and Expert Parallelism
Explain sparse mixture-of-experts routing and expert parallelism, including token dispatch, weighted combination, load balancing, overflow policies, and communication costs.
Machine LearningTechnical Screen - Mistral AIHardMachine Learning EngineerExplain Transformer Internals and Implement Top-p Decoding
Assess understanding of causal transformer decoding mechanics, including attention and KV caching, paired with an implementation of nucleus (top-p) sampling with temperature scaling.
Machine LearningTechnical ScreenTransformersSampling AlgorithmsLLM Inference - Mistral AIMediumSoftware EngineerExplain the Forward and Reverse Processes of Diffusion Models
Explain Gaussian diffusion corruption, timestep-conditioned denoising, noise-prediction training, iterative reverse sampling, latent representations, and guidance tradeoffs.
Machine LearningTechnical Screen - MixpanelMediumData ScientistValidate Features That Predict User Retention
Learn to evaluate retention features with leakage-safe time windows, cohort validation, baselines, ablations, and calibrated predictions.
Machine LearningTechnical Screen - NVIDIAMediumSoftware EngineerCompare deep learning framework trends
Compare deep learning framework trends 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 LearningTechnical Screen - NVIDIAMediumSoftware EngineerDerive MLP shapes and explain PyTorch broadcasting
This question tests the ability to calculate matrix transformation dimensions in a Multilayer Perceptron (MLP) and explains the rules governing PyTorch broadcasting when performing operations between tensors of different shapes.
Machine LearningTechnical ScreenPyTorchLinear AlgebraTensors - NVIDIAMediumSoftware EngineerExplain Transformers and QKV matrices
This question evaluates conceptual and mathematical understanding of the Transformer self-attention mechanism, including how query, key, and value matrices are derived and used. It assesses depth of knowledge in modern deep learning architectures, commonly asked in machine learning and software engineering interviews to test reasoning about sequence modeling and attention-based design.
Machine LearningTechnical Screen - NVIDIAMediumMachine Learning EngineerExplain bias-variance, calibration, and model drift
This question tests your conceptual understanding of model performance degradation over time, the significance of calibrated outputs for decision-making, and the fundamental trade-off between bias and variance.
Machine LearningTechnical ScreenModel EvaluationProduction MLBias-Variance - NVIDIAHardSoftware EngineerExplain optimization and tensor vs pipeline parallelism
This question evaluates knowledge of deep learning optimization techniques (quantization, pruning, knowledge distillation, kernel/operator fusion, memory and throughput optimizations) and model parallelism strategies (tensor versus pipeline), measuring competency in performance engineering, scalability, communication patterns and system-level trade-offs for training and inference. It is commonly asked to assess an engineer's ability to reason about practical and conceptual trade-offs, collectives, bottlenecks and mitigations in distributed and resource-constrained environments, and it falls under the Machine Learning/Deep Learning domain requiring both conceptual understanding and practical application.
Machine LearningTechnical Screen - NatooraMediumData AnalystWhen use LLMs for reporting?
This question assesses the architectural trade-offs, reliability concerns, and suitability of using LLMs for automated business reporting tasks compared to traditional deterministic methods.
Machine LearningTechnical ScreenLLMRAGReporting - NatooraMediumData AnalystWhy use LLMs for daily summaries?
This question evaluates a candidate's ability to justify tooling and architecture choices for automated daily summaries, comparing LLM-based natural language generation with rules-based or templated alternatives while accounting for data sources, consumer intent, validation, failure modes, and cost/latency trade-offs.
Machine LearningTechnical Screen - NetflixMediumMachine Learning EngineerCompare Losses and Explain LoRA
This question evaluates understanding of loss functions (mean squared error versus cross-entropy) and parameter-efficient fine-tuning via Low-Rank Adaptation (LoRA), emphasizing probabilistic interpretations, optimization behavior, and low-rank parameterization.
Machine LearningTechnical Screen - NetflixMediumMachine Learning EngineerExplain self-attention, LoRA, Adam vs SGD, ViT
This question evaluates understanding of modern Machine Learning/Deep Learning topics, including self-attention mechanics (queries, keys, values and scaled logits), Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning and memory savings, optimizer behavior (Adam versus SGD with momentum), and architectural trade-offs between Vision Transformers and CNNs including patch-size considerations. It is categorized under Machine Learning and is commonly asked because it probes both conceptual understanding and practical application—testing reasoning about training dynamics, model scaling, fine-tuning strategies, and resource/performance trade-offs.
Machine LearningTechnical Screen - NetflixMediumMachine Learning EngineerExplain tokenization and Transformer variants
This question evaluates understanding of tokenization techniques and Transformer architecture, covering competencies in subword and SentencePiece-style tokenizers, Transformer block internals, and comparisons of modern architectural variants and trade-offs.
Machine LearningTechnical Screen - NetflixHardMachine Learning EngineerL1 vs L2 Normalization: Definitions, Geometry and When to Use Each
A machine learning fundamentals question asking how L1 normalization differs from L2 normalization of a vector. It tests precise definitions, what each normalized vector represents geometrically, when each is the right choice, and the ability to keep normalization distinct from L1 and L2 regularization.
Machine LearningTechnical Screen - NewsBreakMediumMachine Learning EngineerDerive and implement calibration via temperature scaling
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 Derive and implement calibration via temperature scaling states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Machine LearningTechnical Screen - NewsBreakHardMachine Learning EngineerDesign approach for class imbalance
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 approach for class imbalance states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
Machine LearningTechnical Screen - NewsBreakMediumSoftware EngineerFind Optimal Piecewise Constant Regression Parameters
This problem tests the ability to derive optimal constants for a piecewise regression model with a single split point and to implement an efficient search algorithm to minimize the sum of squared errors.
Machine LearningTechnical ScreenRegressionOptimizationPrefix Sums - NextdoorMediumMachine Learning EngineerBuild a model using only pandas/numpy
This question evaluates proficiency in applied machine learning competencies including data preprocessing, categorical encoding, feature scaling, implementing baseline models and optimization using numpy/pandas, and selecting appropriate evaluation metrics.
Machine LearningTechnical Screen - NikeMediumSoftware EngineerWrite Pseudocode for Embedding Creation and Vector Search
This problem tests the ability to design a robust production pipeline for generating text embeddings and performing efficient, metadata-aware vector retrieval.
Machine LearningTechnical ScreenEmbeddingsVector DBData Pipelines - OneMain FinancialEasyData ScientistExplain decision trees and tree ensembles
This question evaluates understanding of decision trees, splitting criteria for classification versus regression, hyperparameter effects on the bias–variance trade-off, and the mechanics and rationale behind tree-based ensemble methods in the Machine Learning domain.
Machine LearningTechnical Screen - OneMain FinancialHardData ScientistSelect and tune XGBoost hyperparameters
This question evaluates skills in selecting and tuning XGBoost hyperparameters, managing severe class imbalance and sparse one‑hot encodings, handling missing values, and designing compute‑efficient training and grouped cross‑validation to prevent user‑level leakage.
Machine LearningTechnical Screen - OpenAIHardMachine Learning EngineerBuild and troubleshoot image classification and backprop
Build and troubleshoot image classification and backprop 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 LearningTechnical Screen - OpenAIMediumMachine Learning EngineerDebug MiniGPT and Backpropagate Matmul
This question evaluates proficiency in debugging PyTorch transformer implementations, reasoning about attention mechanics and causal masking, implementing key–value caching for autoregressive decoding, and constructing provably correct backward passes for matrix multiplications and custom autograd.Functions.
Machine LearningTechnical Screen - OpenAIMediumSoftware EngineerDebug a Machine Learning Pipeline
This question evaluates a candidate's ability to diagnose production machine learning failures, covering competencies in data quality, data and concept drift detection, model versioning and deployment checks, and operational debugging within an MLOps context.
Machine LearningTechnical Screen - OpenAIMediumMachine Learning EngineerDebug a Transformer Implementation and Implement a KV Cache for Decoding
Practice ML coding question on Transformer language models: find and fix several deliberately planted bugs in a decoder-only Transformer implementation, then implement key-value caching from scratch for autoregressive generation. Tests attention mechanics, tensor-shape reasoning, causal masking, position handling, and verification against full recomputation.
Machine LearningTechnical Screen - OpenAIHardSoftware EngineerDebug a failing ML classifier
This question evaluates a candidate's ability to diagnose a poorly generalizing ML classifier, testing practical knowledge of data leakage, feature drift, and model calibration. It assesses applied machine learning debugging skills — including cross-validation design and error analysis — commonly tested in senior engineering and ML roles.
Machine LearningTechnical Screen
Mistral AI
Mixpanel
NVIDIA
Netflix
Nextdoor
OneMain Financial
OpenAI