practice a little every day, paws crossed ♡
ML System Design 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 1–30 of 186 results
- AMDMediumSoftware EngineerCompare Single-Agent and Multi-Agent Designs
Compare single-agent and multi-agent systems through task independence, specialization, review isolation, coordination cost, shared-state control, and evidence-based integration.
ML System DesignOnsite - AMDMediumSoftware EngineerEvaluate Agents That Generate or Optimize Kernels and Compiler Code
Evaluate kernel and compiler agents with bounded transformation spaces, isolated execution, differential correctness checks, numerical tolerances, representative benchmarks, and reviewable evidence.
ML System DesignOnsite - AMDMediumSoftware EngineerTrace an LLM Request Through a Paged-KV Inference Engine
Trace LLM inference from request admission through prefill and decoding, explaining paged KV block tables, continuous batching, cache lifetime, and latency tradeoffs.
ML System DesignOnsite - AdobeHardMachine Learning EngineerDesign a natural-language AEP Q&A assistant
This interview question evaluates ML product requirements, data/labeling, modeling, serving architecture, evaluation, monitoring, and trade-offs in a realistic interview setting. A strong answer for Design a natural-language AEP Q&A assistant states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
ML System DesignOnsite - AdobeHardMachine Learning EngineerOptimize LLM Training and Serving
This question tests the ability to diagnose hardware utilization bottlenecks in LLM workloads and design architectural optimizations to improve throughput and latency under constrained GPU memory resources.
ML System DesignOnsiteLLMGPU-ArchitecturePerformance-Engineering - AirbnbMediumMachine Learning EngineerDesign User Embedding Semantic Search
This question evaluates competency in ML system design for recommendation and semantic retrieval, covering user and listing representation learning, two-stage retrieval and ranking architectures, training objectives and label design, bias correction from interaction logs, and evaluation and experimentation practices.
ML System DesignOnsite - AirbnbMediumMachine Learning EngineerDesign a Family-Friendly Listing Classifier
This question evaluates proficiency in machine learning system design, including problem formulation tied to product objectives, labeling strategy, feature engineering, model selection, evaluation metrics, robustness to adversarial labels, fairness considerations, and cold-start handling.
ML System DesignOnsite - AirbnbHardSoftware EngineerDesign a dynamic rental pricing system
This question evaluates skills in production machine learning system design for pricing, including problem formulation, data and feature engineering, modeling and uncertainty management, online inference and scalability, experimentation and guardrails, and considerations like fairness and cold-start handling.
ML System DesignOnsite - AirbnbMediumMachine Learning EngineerGenerate Customer-Support Instructions from Company Policies
Design a policy-grounded support RAG system with ordered instructions, applicability checks, procedural evaluation, citations, and version-aware debugging.
ML System DesignOnsite - AirbnbMediumMachine Learning EngineerRank Home Search Results Without a Text Query
Design a home-search ranker without query text, covering structured intent, training bias, cold start, online evaluation, and production debugging.
ML System DesignOnsite - AirtableMediumSoftware EngineerDesign NL-to-Formula assistant for Airtable
Airtable software-engineer onsite ML system design question: design an assistant that turns natural-language requests into the product's formula language, grounded in the live table schema, and optionally applies them to the base via the Airtable API. It tests LLM orchestration with structured outputs / a typed IR, schema grounding and type checking, ambiguity handling, static + dynamic formula validation, prompt-injection safety, confirmation-gated writes, latency trade-offs, and offline/online evaluation.
ML System DesignOnsite - AmazonHardApplied ScientistBuild an end-to-end ML pipeline
Build an end-to-end ML pipeline evaluates ML product requirements, data/labeling, modeling, serving architecture, evaluation, monitoring, and trade-offs in a realistic interview setting. A strong answer states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
ML System DesignOnsite - AmazonHardApplied ScientistDeep-dive your GenAI project architecture
Deep-dive your GenAI project architecture evaluates ML product requirements, data/labeling, modeling, serving architecture, evaluation, monitoring, and trade-offs in a realistic interview setting. A strong answer states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
ML System DesignOnsite - AmazonHardApplied ScientistDesign a Multimodal Neural Network
This question evaluates a candidate's competency in designing production-grade multimodal machine learning systems, including architecture choices for text and image encoders, cross-modal fusion strategies, training objectives for joint retrieval and classification, robustness to missing or noisy modalities, and considerations for scalability and low-latency serving. Commonly asked in ML system design interviews to assess both conceptual understanding and practical application of machine learning engineering principles, it falls under the ML System Design domain and probes abilities in model alignment, evaluation metrics, deployment trade-offs, and domain adaptation strategies.
ML System DesignOnsite - AmazonMediumSoftware EngineerDesign a Platform for Training and Serving ML Models
This problem tests the ability to design an end-to-end MLOps platform capable of handling the full lifecycle of machine learning models, from experimentation to production deployment.
ML System DesignOnsiteMLOpsSystem DesignScalability - AmazonMediumApplied ScientistDesign a computer-use agent end-to-end
This problem evaluates your ability to design a multimodal agent capable of interpreting UI elements and executing sequences of actions to complete user-defined tasks on a computer screen.
ML System DesignOnsiteVLMReinforcement LearningMultimodal - AmazonMediumApplied ScientistDesign an LLM quality validation system
This question evaluates an engineer's competency in ML system design for validating large language models, testing knowledge of evaluation metrics, validation scopes from internal numerics to final responses, system architecture for automated validation pipelines, and operational concerns within the ML System Design domain; it requires both conceptual architecture understanding and practical application-level thinking. It is commonly asked to assess the ability to reason about correctness, safety, regression risk, scalability, reproducibility, and monitoring trade-offs when deploying production-grade validation pipelines and to gauge familiarity with complementary evaluation methods and end-to-end data flows.
ML System DesignOnsite - AmazonHardApplied ScientistDesign systems for global request detection and labeling
This problem tests the architecture of a high-throughput streaming system capable of detecting anomalies in real-time, managing extreme class imbalance for labeling, and maintaining low-latency inference at a global scale.
ML System DesignOnsiteStreamingReal-time InferenceImbalanced Learning - AmazonMediumApplied ScientistExplain parallelism and collectives in training
This question evaluates a candidate's competency in designing scalable distributed training systems, covering parallelism strategies (data, model/tensor, pipeline), communication collectives (all-reduce, all-gather, reduce-scatter, broadcast), and tensor-level layer partitioning such as column- and row-parallel splits.
ML System DesignOnsite - AnthropicMediumSoftware EngineerDesign GPU inference request batching
This question evaluates a candidate's competency in ML System Design, focusing on GPU-based inference batching, scheduling, autoscaling, and the operational concerns of routing, compatibility, and fault-tolerance.
ML System DesignOnsite - AnthropicMediumSoftware EngineerDesign Model Weight Distribution
This question evaluates a candidate's competency in large-scale ML system design and distributed systems, focusing on weight file distribution, versioning and rollout strategies, consistency models, integrity verification, access control, rollback mechanisms, and operational scalability.
ML System DesignOnsite - AnthropicMediumSoftware EngineerDesign Safe Distribution and Activation of Model Weights
This problem tests the ability to architect a robust, secure, and atomic deployment system for large binary artifacts (model weights) across a distributed inference cluster.
ML System DesignOnsiteDistributed SystemsMLOpsSystem Design - AnthropicHardSoftware EngineerDesign a GPU inference API
This Anthropic ML system design onsite asks you to design a multi-tenant, GPU-backed inference API that serves many models and versions -- including large autoregressive LLMs -- under explicit latency SLOs. It spans API and schema design, streaming and async jobs, continuous batching with prefill/decode separation, KV-cache and GPU memory management, multi-model hosting on shared GPUs, heterogeneous autoscaling and placement, multi-region routing, canary rollout, and reliability and cost controls. The signature probe is the diagnostic scenario where CPU utilization is low but the GPUs are saturated.
ML System DesignOnsite - AnthropicHardSoftware EngineerDesign a batch inference API
This question evaluates a candidate's ability to design asynchronous batch inference APIs and systems, including API schema and job lifecycle design, idempotency semantics, queueing and worker scaling, batching and accelerator utilization, rate limiting, observability, and error handling.
ML System DesignOnsite - AnthropicHardSoftware EngineerDesign a high-concurrency LLM inference service
This problem evaluates your ability to design a scalable LLM inference serving platform, focusing on throughput optimization, memory constraints, and scheduling strategies for long-running inference requests.
ML System DesignOnsiteLLMInferenceGPU - AnthropicHardSoftware EngineerDesign a low-latency ML inference API
This question evaluates competency in ML system design for real-time, low-latency inference APIs, including multitenancy, SLO/SLI definition, feature retrieval, model serving and rollout strategies, observability, cost control, and security/compliance within the ML System Design category.
ML System DesignOnsite - AnthropicMediumMachine Learning EngineerDesign a model downloader
This question assesses the architectural design of a distributed, secure, and resilient system capable of deploying large-scale machine learning models to heterogeneous edge devices.
ML System DesignOnsiteSystem DesignMLOpsDistributed Systems - AnthropicHardSoftware EngineerDesign a prompt processing backend
Design a prompt processing backend evaluates ML product requirements, data/labeling, modeling, serving architecture, evaluation, monitoring, and trade-offs in a realistic interview setting. A strong answer states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.
ML System DesignOnsite - AnthropicHardMachine Learning EngineerDesign an inference routing and scheduling layer
This question evaluates system-design and production machine learning engineering skills, specifically distributed systems, routing and scheduling, multi-tenant isolation, caching, dynamic batching, and capacity planning for heterogeneous GPU/CPU inference backends.
ML System DesignOnsite - AnthropicHardSoftware EngineerEstimate FFN Compute, Memory, and Sharding Communication
Estimate standard FFN FLOPs, parameter and activation bytes, and sharding communication, then compare compute, HBM, and network limits with explicit layout assumptions.
ML System DesignOnsite
Adobe
Airbnb
Airtable
Amazon
Anthropic