ML System Design Interview Questions

Showing 301–330 of 332 results

• TikTokHard·Machine Learning Engineer
  Design query generation to maximize CTR

  Design query generation to maximize CTR 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
• TikTokMedium·Software Engineer
  Design system to detect privacy-leak records

  This question evaluates a candidate's ability to design scalable ML-driven systems for detecting and classifying privacy-sensitive and PII-containing records across structured and unstructured data, testing competencies in data engineering, machine learning (including deep learning and LLM/RAG integrations), system architecture, and privacy/security considerations. It is commonly asked to probe reasoning about functional and non-functional requirements, trade-offs in detection and classification approaches, evaluation metrics like precision and recall, feedback loops and operational scaling, and it falls under ML system design with a practical, application-level focus rather than purely conceptual abstraction.

  ML System DesignTechnical Screen
• TikTokMedium·Machine Learning Engineer
  Design video captioning under compute limits

  This question evaluates expertise in ML system design for multimodal large models, covering deployment under compute and GPU memory constraints as well as large-scale retrieval and processing of video captions and embeddings.

  ML System DesignTechnical Screen
• TTowerHard·Data Scientist
  Debug Oscillating GPU Utilization During Training

  Design a systematic debugging and architectural remediation strategy for a distributed deep learning training cluster exhibiting severe GPU utilization oscillation between 90% and 20%.

  ML System DesignTechnical Screendistributed-trainingml-system-designgpu-optimization
• TubiMedium·Machine Learning Engineer
  ML System Design: Movie Recommendation Model and Pipeline (AI-Assisted Round)

  This question tests ML system design competency, specifically the ability to architect end-to-end recommendation pipelines covering retrieval, ranking, feature engineering, and low-latency serving at scale. It assesses practical knowledge of two-stage recommender systems, implicit feedback modeling, cold-start handling, and critical evaluation of AI-generated code — skills central to machine learning engineering interviews.

  ML System DesignTechnical Screen
• TubiMedium·Machine Learning Engineer
  ML System Design: Thumbnail Selection for a Streaming Catalog

  This ML system design question tests a candidate's ability to architect an end-to-end personalization and ranking system, covering problem framing, reward modeling, and low-latency serving at scale. It evaluates practical knowledge of contextual bandits, engagement-signal design, cold-start handling, and off-policy evaluation — core competencies for machine learning engineering roles.

  ML System DesignTechnical Screen
• Two SigmaMedium·Software Engineer
  Design GenAI Fine-Tuning and Agent Tradeoffs

  Design an enterprise GenAI research agent platform, evaluating trade-offs between fine-tuning methods (Full, LoRA, QLoRA) versus RAG, alongside agent orchestration, structured outputs, and safety controls.

  ML System DesignTechnical ScreenLLM Fine-TuningAI AgentsModel Serving
• Two SigmaHard·Data Scientist
  Predict Citi Bike Demand at a Specific NYC Station

  This question evaluates time-series forecasting, demand estimation, and ML system-design competencies, focusing on problem framing, handling censored observations, data integration, model selection, and evaluation under operational constraints.

  ML System DesignTechnical Screen
• Two SigmaHard·Data Scientist
  Predicting Stock Prices from Twitter Data

  This question evaluates competency in ML system design for integrating NLP-derived signals from social media with time-series financial modeling, including feature extraction, timestamp alignment, and handling low signal-to-noise ratios.

  ML System DesignTechnical Screen
• UberMedium·Machine Learning Engineer
  Design a feed ranking system

  This question evaluates a candidate's competency in designing end-to-end machine-learning-based feed ranking systems, including setting ranking objectives, candidate generation and filtering, feature design, model training and serving, and operational concerns like freshness, diversity, and scalability.

  ML System DesignTechnical Screen
• UberMedium·Machine Learning Engineer
  Design a restaurant recommendation system

  An Uber MLE onsite ML system design question: design a personalized restaurant recommendation system for a food delivery marketplace's home feed. It tests candidate generation and ranking, feature engineering and training data, cold-start and exploration, low-latency serving, and offline/online evaluation, plus marketplace concerns like availability, ETA, diversity, fairness, and business rules.

  ML System DesignOnsite
• UberHard·Machine Learning Engineer
  Design real-time grid ETA for drivers

  This question evaluates a candidate's competency in real-time ML system design, covering streaming data ingestion, GPS noise handling and denoising, online feature computation, low-latency model serving, and operational monitoring.

  ML System DesignOnsite
• UberMedium·Machine Learning Engineer
  Present a Marketplace ML Project Deep Dive

  This question evaluates a candidate's competence in end-to-end ML system design, product-oriented machine learning, and cross-functional skills such as feature engineering, model deployment, online experimentation, monitoring, stakeholder communication, and measuring business impact.

  ML System DesignTechnical Screen
• UberMedium·Machine Learning Engineer
  Where to apply ML in a task flow from customer request to driver-uploaded evidence

  An ML system design discussion about a task platform: walk the end-to-end flow from a customer submitting a task to a driver completing it and uploading evidence, and identify where machine learning and LLMs add value. Tests prioritization, model framing, labels, evaluation and risk handling.

  ML System DesignTechnical Screen
• UUnityMedium·Software Engineer
  Design a Feature Store for Offline Training and Low-Latency Online Serving

  Design a feature store that ingests high-volume event data, produces point-in-time correct training sets, and serves the latest features at low latency in production. It tests streaming and batch feature computation, leakage-free historical joins, online store design, and keeping training and serving consistent.

  ML System DesignOnsite
• VantaMedium·Software Engineer
  Review and Debug an AI Chatbot

  Design an end-to-end debugging, observability, and evaluation architecture for a multi-tenant enterprise AI compliance chatbot experiencing hallucinations, latency spikes, and policy violations.

  ML System DesignOnsiteLLM ObservabilityRAGData Privacy
• VoleonHard·Machine Learning Engineer
  Design a cold-start video recommender

  This problem tests the ability to architect a recommendation system that provides personalized content for new users or items with zero historical interaction data.

  ML System DesignTechnical ScreenRecommender SystemsCold StartMulti-Armed Bandits
• VoleonHard·Machine Learning Engineer
  Estimate Fine-Tuning Memory Requirements

  Learn to estimate full and parameter-efficient fine-tuning memory with a transparent ledger for model state, activations, sharding, and peak overhead.

  ML System DesignTechnical Screen
• Walmart LabsEasy·Machine Learning Engineer
  Design a Conversational Agent for Finding Vacation Rentals

  Design a multi-turn assistant that turns a traveler's free-form trip description into structured, grounded rental search results. Tests where to use an LLM versus deterministic search, clarification strategy, safety against hallucination and injection, and evaluation against classic search.

  ML System DesignOnsitellm-agentssearchretrieval
• Walmart LabsEasy·Machine Learning Engineer
  Design an Agentic Search Experience

  Design an agentic search experience with clarifying dialogue, structured constraints, grounded retrieval, bounded tool use, and evaluation against conventional search.

  ML System DesignOnsite
• Walmart LabsEasy·Machine Learning Engineer
  Design an item category prediction system

  This question tests the ability to design an end-to-end classification system for assigning retail items into a hierarchical category structure, focusing on feature selection, model architecture, and production deployment.

  ML System DesignOnsiteClassificationNLPMulti-modal
• WayfairMedium·Applied Scientist
  Rank Homepage Modules for an E-Commerce Product

  Rank e-commerce homepage modules using business objectives, seasonal eligibility, slot effects, slate diversity, cold-start exploration, and page-level experiments.

  ML System DesignOnsite
• WayfairMedium·Applied Scientist
  Set Bids for Search Advertising from Business Value

  Design search-ad bidding from expected business value, with budget pacing, delayed conversion feedback, auction assumptions, and incremental-profit evaluation.

  ML System DesignTechnical Screen
• WaymoMedium·Machine Learning Engineer
  Design Large-Scale Inference Serving

  This question evaluates understanding of large-scale ML inference systems, assessing competencies in capacity planning, latency and tail-latency engineering, memory and bandwidth estimation, hardware selection (CPUs/GPUs/specialized accelerators), batching and caching trade-offs, and reliability concerns such as out-of-memory prevention and recovery. It is commonly asked to test practical system-design skills for production deployment by requiring back-of-the-envelope QPS and resource estimates and reasoning about operational trade-offs; this belongs to the ML system design category and emphasizes practical application over purely conceptual theory.

  ML System DesignTechnical Screen
• WaymoMedium·Software Engineer
  Design a Hybrid Evaluation Platform

  This problem tests your ability to design a multi-modal evaluation infrastructure that balances automated LLM-based grading with human-in-the-loop (HITL) verification to ensure high-fidelity ML model performance metrics.

  ML System DesignOnsiteMLOpsData InfrastructureHuman-in-the-loop
• WhatnotMedium·Machine Learning Engineer
  Design trending livestream discovery

  This question evaluates expertise in designing end-to-end ML-driven recommendation systems, including competencies in real-time feature engineering, candidate generation, model serving, business-rule integration, monitoring, experimentation, and operational trade-offs for live content.

  ML System DesignTechnical Screen
• WWorkdayMedium·Software Engineer
  Design AI-Powered Document Search

  This question assesses the ability to design an end-to-end, scalable pipeline for ingesting, processing, and indexing heterogeneous documents (PDFs, images, text files) to support AI-driven semantic search.

  ML System DesignOnsiteSystem DesignML EngineeringPipelines
• XPengHard·Machine Learning Engineer
  Design and train a PPO pipeline

  This question evaluates proficiency in designing and training Proximal Policy Optimization (PPO) pipelines, covering environment interfacing, observation/action design, reward shaping, rollout and advantage estimation, hyperparameterization, normalization, parallelization, evaluation, and sim‑to‑real considerations.

  ML System DesignTechnical Screen
• XXometryMedium·Machine Learning Engineer
  Optimize Model Serving Under 200ms

  This question evaluates competency in deploying and optimizing machine learning models for low-latency online inference, covering model serving, latency profiling, hardware considerations, and managing accuracy–latency trade-offs within a 200ms SLO in the ML System Design domain.

  ML System DesignTechnical Screen
• EeBayEasy·Applied Scientist
  Design fast query-to-listing retrieval over tens of millions of listings

  An ML system design question on retrieving relevant listings for free-text search queries across a catalog of tens of millions of items with low latency. It tests candidate generation, indexing, embedding training, freshness, filtering and scaling, plus the offline and A/B test metrics used to evaluate retrieval.

  ML System DesignTechnical Screen