ML System Design interview questions

Showing 211–240 of 332 results

• Design a Production Retrieval-Augmented Generation PipelineMedium

  This problem tests the ability to design an end-to-end RAG system, focusing on document processing, embedding strategies, retrieval mechanisms, and ensuring accuracy through grounding.

  NetappSoftware EngineerML System DesignOnsite
• Build a Recommendation System and Conversational Interface from ScratchHard

  Design an initial recommendation system, then extend it with a chatbot that can retrieve and explain recommendations while respecting the same eligibility and ranking rules. Connect data and model choices to serving architecture, latency and throughput, evaluation, monitoring, failure modes, and iteration.

  NetflixSoftware EngineerML System DesignOnsite
• Design an ML Platform PortalEasy

  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.

  NetflixMachine Learning EngineerML System DesignOnsite
• Review a Feature Pipeline PR for Production Risks, Then Serve Features by FreshnessHard

  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.

  NetflixMachine Learning EngineerML System DesignTechnical Screen
• Build an end-to-end ML classification pipelineMedium

  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.

  NextdoorMachine Learning EngineerML System DesignTechnical Screen
• Design a PDF Ingestion and Retrieval-Augmented Generation PipelineMedium

  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.

  NikeSoftware EngineerML System DesignTechnical Screen
• Design a Shared Distributed ML Training PlatformHard

  Design a multi-tenant distributed machine learning training platform that orchestrates GPU clusters, enforces team quotas, guarantees gang scheduling, and handles node-level checkpointing and recovery.

  NuroSoftware EngineerML System DesignOnsite
• Design an Inference PipelineHard

  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.

  NuroMachine Learning EngineerML System DesignTechnical Screen
• Design LLM search handling long token inputsHard

  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.

  OpenAIMachine Learning EngineerML System DesignOnsite
• Design a Real-Time Sensor Intelligence SystemMedium

  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.

  OpenAIMachine Learning EngineerML System DesignOnsite
• Design a Retrieval-Augmented Generation (RAG) systemHard

  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.

  OpenAISoftware EngineerML System DesignTechnical Screen
• Design a Text-to-Video Generation Platform (Sora-style)Hard

  This problem evaluates your ability to design a distributed ML infrastructure that handles high-latency, resource-intensive inference jobs while ensuring scalability, reliability, and content safety.

  OpenAISoftware EngineerML System DesignOnsite
• Design a Text-to-Video Generation ServiceMedium

  This question tests the ability to design a scalable, reliable asynchronous inference pipeline for resource-intensive generative models, focusing on task orchestration, GPU scheduling, and latency management.

  OpenAISoftware EngineerML System DesignTechnical Screen
• Design a Text-to-Video Generation SystemHard

  This question evaluates a candidate's competency in designing scalable ML inference platforms, including GPU resource management and scheduling, asynchronous job orchestration and state-machine-driven job lifecycles, failure classification and recovery, artifact storage, rate limiting, and monitoring for quality and latency.

  OpenAISoftware EngineerML System DesignOnsite
• Design a Video Generation Service with GPU Fleet ManagementMedium

  Tests the ability to design an end-to-end distributed ML inference system for compute-intensive video generation, focusing on GPU scheduling, job lifecycle management, fault tolerance, and cost efficiency.

  OpenAISoftware EngineerML System DesignTechnical Screen
• Design a chatbot (system design)Medium

  This question evaluates system design skills for ML-powered chatbots with a front-end focus, testing understanding of client-side privacy and storage lifetimes, streamed response delivery, stateless relay architectures, authentication boundaries, rate limiting, and failure-mode handling.

  OpenAISoftware EngineerML System DesignTechnical Screen
• Design a chatbot fallback for unknown questionsHard

  This question evaluates a candidate's competency in ML system design, focusing on handling model uncertainty, retrieval-augmented components, tool integration, decision policies, and operational evaluation within the ML System Design domain.

  OpenAIMachine Learning EngineerML System DesignOnsite
• Design a harmful video content moderation systemHard

  This question evaluates a candidate's competency in designing scalable, multi-modal machine learning systems for content moderation, covering architecture, model strategy, labeling and human-in-the-loop workflows, metrics, auditability, and defenses against adversarial evasion.

  OpenAIMachine Learning EngineerML System DesignOnsite
• Design a low-latency RAG systemHard

  This question evaluates ML system design skills, specifically the ability to architect retrieval-augmented generation pipelines under strict latency, cost, and multi-tenancy constraints. It tests how candidates reason about vector search, re-ranking, and LLM integration at production scale — a core competency for senior machine learning engineering roles.

  OpenAIMachine Learning EngineerML System DesignTechnical Screen
• Design a production RAG systemHard

  An OpenAI ML system design interview question (MLE technical screen): design a production, multi-tenant retrieval-augmented generation (RAG) system for enterprise document QA. The model answer covers ingestion and chunking, embedding selection, ANN/vector indexing (HNSW vs IVF-PQ), hybrid retrieval and cross-encoder re-ranking, prompt orchestration with citation grounding, hallucination mitigation, caching and freshness, multilingual and PII/safety handling, scalability and disaster recovery, observability and offline/online evaluation, an API and data schema, cost controls, and a phased rollout. It tests trade-off reasoning across recall, latency, cost, and compliance.

  OpenAIMachine Learning EngineerML System DesignTechnical Screen
• Design a recommendation system end-to-endHard

  This question evaluates a candidate's competency in large-scale machine learning system design, including architecture for candidate generation and ranking, feature engineering across real-time and batch pipelines, training and serving workflows, and monitoring for fairness and safety.

  OpenAIMachine Learning EngineerML System DesignOnsite
• Design a response-ranking ML systemHard

  Design a response-ranking ML system 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.

  OpenAISoftware EngineerML System DesignTechnical Screen
• Design an AWS fine-tuning platform for LLMsHard

  This question evaluates a candidate's competency in designing cloud-native ML platforms for fine-tuning large language models, covering distributed training, multi-tenant security and isolation, cost controls, reproducibility, observability, checkpointing, and deployment workflows.

  OpenAIMachine Learning EngineerML System DesignOnsite
• Design an Agent Harness and Evaluation SystemMedium

  Design a safe harness and evaluation platform for a tool-using AI agent. Address isolated execution, repeatable task sets, trajectory tracing, deterministic and rubric-based graders, repeated trials, privacy, regression gates, and reward-hacking risks.

  OpenAIMachine Learning EngineerML System DesignOnsite
• Design an ML search systemHard

  This question evaluates system-design and information-retrieval competencies for machine-learning-powered enterprise document search, covering ingestion and indexing pipelines, hybrid lexical and semantic retrieval, feature generation and ranking, multi-tenant access control, and security/compliance.

  OpenAIMachine Learning EngineerML System DesignTechnical Screen
• Design an ML search system with RAGHard

  Design an ML search system with RAG 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.

  OpenAIMachine Learning EngineerML System DesignTechnical Screen
• Design an OOD detection systemMedium

  This question tests the ability to design an end-to-end system for detecting out-of-distribution (OOD) data in production LLMs to ensure reliability and safety.

  OpenAIMachine Learning EngineerML System DesignTechnical Screen
• Design an enterprise RAG assistant for internal docsHard

  This question evaluates expertise in designing and training Retrieval-Augmented Generation (RAG) systems, including retriever, evaluator (reranker/verifier/filter), and generator components, with emphasis on model architecture choices, training objectives, data preparation under privacy and document-permission constraints, and evaluation strategies for grounded answers with citations. It is commonly asked to probe advanced ML system design and operationalization skills for mitigating hallucination, stale or conflicting sources, and long-document retrieval; the category is ML System Design and the level is practical application-focused with detailed modeling and training considerations.

  OpenAISoftware EngineerML System DesignTechnical Screen
• Design an image/video near-duplicate detection systemHard

  This question evaluates competency in ML system design and large-scale multimedia retrieval, focusing on perceptual fingerprinting versus embedding strategies, scalable indexing and nearest-neighbor retrieval, and robustness to resizing, re-encoding, watermarks, minor edits, and adversarial manipulations.

  OpenAIMachine Learning EngineerML System DesignOnsite
• Design and optimize a RAG systemHard

  An OpenAI machine learning engineer onsite ML system design question: design, optimize and evaluate a production Retrieval-Augmented Generation (RAG) system that answers questions over a private corpus with citations. The merged answer covers the full pipeline — ingestion and layout-aware parsing, structure-aware chunking, embeddings and versioning, hybrid BM25 plus vector retrieval with RRF fusion, cross-encoder reranking, grounded generation with forced citations, abstention and a fallback ladder, ACL enforcement during retrieval, and the insert/edit/delete freshness lifecycle. It then gives a stage-by-stage evaluation plan (chunk answerability, hit-rate@K, recall@K, nDCG, faithfulness, citation quality, end-to-end success), how to bootstrap labels with no gold set, and follow-ups on debugging a wrongly cited document, embedding-model upgrades, multi-hop versus list-all queries, near-duplicates, conflicting sources and validating an LLM judge.

  OpenAIMachine Learning EngineerML System DesignOnsite