ML System Design Interview Questions

Showing 61–90 of 138 results

• LinkedInHard·Machine Learning Engineer
  Design a Model That Predicts Whether a Member Clicks a Displayed Job

  An ML system design question: predict whether a member will click a job displayed to them, using member features, job content and interaction history. It tests defining the supervision signal and training data, choosing a loss, preventing data leakage, building member and job embeddings, and laying out the training and serving components.

  ML System DesignTechnical Screen
• LinkedInMedium·Machine Learning Engineer
  Design a Personalized Feed and Compare Ranking Objectives

  Design an end-to-end personalized professional feed system and compare pointwise, pairwise, and listwise learning-to-rank formulations across offline training, online serving, and business metrics.

  ML System DesignTechnical Screenml-system-designrecommendation-systemslearning-to-rank
• LinkedInMedium·Machine Learning Engineer
  Design an ML Forecasting and Pacing System for Ad Bidding

  Design an ad forecasting and budget pacing architecture that combines predictive ML with deterministic budget guardrails to optimize campaign delivery across non-stationary traffic.

  ML System DesignTechnical Screenml-system-designad-techtime-series
• Luma AIHard·Software Engineer
  Manage Prompt and Model Behavior in Production

  This question tests the ability to design an end-to-end configuration management and observability system for LLM applications that ensures reproducibility, safety, and rapid recovery from performance drift.

  ML System DesignTechnical ScreenLLMOpsSystem DesignObservability
• MercorMedium·Machine Learning Engineer
  Build an Ollama Eval Harness

  This question evaluates a candidate's ability to design and implement a lightweight evaluation harness for a locally hosted language model, testing competencies in ML system design, service integration, metrics instrumentation, reliability engineering (timeouts, retries), concurrency control, configuration management, and extensibility.

  ML System DesignTechnical Screen
• MetaMedium·Machine Learning Engineer
  Design a Real-Time Question-Answering Chatbot: Training Data, RL Tasks and Rewards

  An AI design question about a chatbot that answers user questions in real time. It tests the low-latency serving and retrieval path, training data collection for fine-tuning and preference learning, reinforcement-learning task and reward design, and the ability to name reward weaknesses and mitigate them.

  ML System DesignTechnical Screen
• MetaMedium·Machine Learning Engineer
  Design a Short-Video Recommendation System

  This question tests your ability to design a multi-stage recommendation pipeline for a high-traffic short-video platform, focusing on candidate retrieval, ranking models, and system scalability.

  ML System DesignTechnical ScreenRecommendation SystemsScalabilityRanking
• MetaHard·Software Engineer
  Design an Automated Ticket Investigation Agent

  This question evaluates a candidate's ability to design AI-enabled agentic systems for automated ticket investigation, covering competencies in ticket understanding, classification and prioritization, multi-source evidence retrieval (logs, metrics, traces, documentation), root-cause diagnosis, remediation orchestration, and human-in-the-loop safety controls. It is commonly asked in the ML system design domain to assess architectural and integration thinking, data retrieval and evaluation strategies, production monitoring and safety considerations, and tests both high-level conceptual architecture and practical application-level implementation concerns.

  ML System DesignTechnical Screen
• MetaHard·Machine Learning Engineer
  Design image and multimodal generation systems

  This question evaluates a candidate's competence in designing end-to-end image and multimodal generation systems, covering data collection and curation, model architecture and conditioning choices, training objectives, safety and content filtering, evaluation metrics, deployment, monitoring, and critical analysis of relevant research.

  ML System DesignTechnical Screen
• MetaMedium·Software Engineer
  Explain an AI System You Designed and the Problem It Solved

  Tests your ability to articulate an end-to-end production AI/ML system you designed, detailing the business justification, technical architecture, evaluation strategy, failure modes, and your individual contributions.

  ML System DesignTechnical Screenml-system-designai-architecturemodel-evaluation
• MetaMedium·Machine Learning Engineer
  Prevent Private Code Leakage in Coding Agents

  This problem tests the ability to design an ML-driven safeguard system that prevents private codebase exposure during the training, fine-tuning, and inference phases of a coding agent.

  ML System DesignTechnical ScreenMLOpsSecurityPrivacy
• MicrosoftMedium·Data Scientist
  Design Product-Description Content Moderation at Marketplace Scale

  Design an ML moderation system for multilingual seller descriptions at marketplace scale. Cover policy-aware labels, severity-based actions, calibrated thresholds, human review and appeals, low-latency serving, selective rescans, auditability, drift, and adversarial abuse.

  ML System DesignTechnical Screen
• MicrosoftMedium·Machine Learning Engineer
  Design quality checks for spreadsheet LLM data

  This problem tests the ability to design an end-to-end data validation pipeline for spreadsheet data and determine the necessity of fine-tuning a Large Language Model (LLM) for specific structured data tasks.

  ML System DesignTechnical ScreenLLMData ValidationFine-tuning
• MicrosoftEasy·Machine Learning Engineer
  Explain Transformers and deploy an LLM safely

  This question evaluates understanding of Transformer architectures and practical LLM deployment competencies, covering attention mechanisms, token and positional representations, computational complexity, and production concerns like latency, cost, quality, safety, and privacy.

  ML System DesignTechnical Screen
• MillenniumMedium·Data Scientist
  Design a Governed Agent for Portfolio Rebalancing

  Design an autonomous, LLM- or ML-driven portfolio rebalancing agent integrated with deterministic guardrails, pre-trade compliance checks, and audit logging. The design must guarantee safety, idempotency, strict separation of concerns, and full state reconstructibility.

  ML System DesignTechnical Screenml-system-designai-agentsrisk-management
• Mistral AIMedium·Machine Learning Engineer
  Build a Small Agent or RAG Tool with the Mistral API

  Design an end-to-end Retrieval-Augmented Generation (RAG) agent using the Mistral API to answer technical queries over internal developer documentation. The question evaluates chunking strategies, dense retrieval, prompt orchestration, latency optimizations, and evaluation methodologies.

  ML System DesignTechnical Screenragml-system-designllm-agents
• Mistral AIHard·Software Engineer
  Build and design a Mistral RAG agent

  This question evaluates a candidate's skills in building a retrieval-augmented generation (RAG) system, covering document ingestion, chunking, embedding generation, vector indexing, retrieval, LLM API-driven streaming completions, short-term conversation memory, and operational reliability features.

  ML System DesignTechnical Screen
• Mistral AIHard·Software Engineer
  Design a PDF-to-Markdown Inference API

  This question evaluates system-design and ML inference orchestration skills, assessing competency in composing multi-stage pipelines that manage heterogeneous resource profiles (CPU, GPU, memory) and trade-offs between latency and throughput.

  ML System DesignTechnical Screen
• NVIDIAMedium·Software Engineer
  Describe model-to-GPU execution pipeline

  Describe model-to-GPU execution 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 DesignTechnical Screen
• NVIDIAMedium·Software Engineer
  Design and benchmark optimized inference pipelines

  Design and benchmark optimized inference pipelines 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 DesignTechnical Screen
• NVIDIAEasy·Software Engineer
  Design real-time fraud detection under 50ms

  This question evaluates expertise in designing low-latency, high-throughput ML-powered systems for online decisioning, covering competencies in real-time inference, feature pipelines, model serving, scaling, and operational reliability within the ML System Design domain.

  ML System DesignTechnical Screen
• NVIDIAHard·Machine Learning Engineer
  Discuss Transformer LLM Design

  Discuss Transformer LLM Design 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 DesignTechnical Screen
• NVIDIAMedium·Software Engineer
  Explain ML compilation optimizations and hardware fit

  This question evaluates a candidate's understanding of ML compiler optimizations and hardware-aware runtime strategies, assessing competencies in techniques such as kernel fusion, quantization, memory planning, scheduling/tiling, layout selection, sparsity, mixed precision, graph-level rewrites and runtime tactics.

  ML System DesignTechnical Screen
• NVIDIAHard·Software Engineer
  Explain ML framework trends

  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 Explain ML framework trends states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.

  ML System DesignTechnical Screen
• NVIDIAMedium·Software Engineer
  How would you optimize large-scale training/inference?

  This problem tests your understanding of performance bottlenecks in large-scale machine learning systems, requiring you to prioritize optimization strategies across memory, compute, and communication dimensions.

  ML System DesignTechnical ScreenML SystemsGPU ArchitecturePerformance Engineering
• NetflixHard·Machine Learning Engineer
  Review a Feature Pipeline PR for Production Risks, Then Serve Features by Freshness

  Review a feature pipeline pull request whose tests all pass and explain what could break once it runs in production, from time leakage and training-serving skew to data quality and scale. Then decide how the same features should be served when the model needs day-old, minute-fresh or request-time values.

  ML System DesignTechnical Screen
• NextdoorMedium·Machine Learning Engineer
  Build an end-to-end ML classification pipeline

  This question evaluates a candidate's competency in building end-to-end tabular classification pipelines, including data loading and splitting, missing-value handling, categorical encoding, feature scaling, model training and comparison, hyperparameter tuning, metric-based evaluation, model persistence, and batch inference.

  ML System DesignTechnical Screen
• NNikeMedium·Software Engineer
  Design a PDF Ingestion and Retrieval-Augmented Generation Pipeline

  This problem tests the ability to design an end-to-end RAG pipeline capable of handling complex document parsing, chunking strategies for citations, and efficient synchronization of updates.

  ML System DesignTechnical ScreenRAGPDF ParsingVector Databases
• NuroHard·Machine Learning Engineer
  Design an Inference Pipeline

  This question evaluates competency in designing production machine-learning inference pipelines, covering model routing, artifact versioning and deployment, feature retrieval at inference time, low-latency/high-availability architectures, monitoring for model quality and data drift, and safe rollout strategies.

  ML System DesignTechnical Screen
• OpenAIHard·Software Engineer
  Design a Retrieval-Augmented Generation (RAG) system

  This question tests the ability to design an end-to-end Retrieval-Augmented Generation (RAG) system, focusing on balancing retrieval accuracy, latency, data freshness, and system reliability.

  ML System DesignTechnical ScreenRAGLLMVector Databases