Interview questions

Review an inference API design for scale

Companies: Anthropic

Fault Tolerance & Failover · LLM Inference & Serving · ML System Design

Last reported Sep 2025

Design a production RAG system

Companies: OpenAI

Embeddings & Vector Search · ML System Design · Retrieval-Augmented Generation

Last reported Aug 2025

Design a chatbot (system design)

Companies: OpenAI

Authentication & Authorization · ML System Design · Real-Time Systems

Last reported Aug 2025

Design an End-to-End ML System

Companies: OpenAI

ML Data Pipelines & Feature Stores · Ranking Models

Last reported Aug 2025

Design enterprise RAG search system

Companies: OpenAI

LLM Applications · Retrieval-Augmented Generation

Last reported Aug 2025

Predict future time-series values

Companies: Jane Street

ML System Design

Last reported Aug 2025

Design a GPU inference API

Companies: Anthropic

GPU Infrastructure · LLM Inference & Serving · ML System Design

Last reported Aug 2025

Design an end-to-end training framework

Companies: Jane Street

ML System Design

Last reported Aug 2025

Design a response-ranking ML system

Companies: OpenAI

Model Evaluation · Ranking Models

Last reported Jul 2025

Design Pin recommendation system

Companies: Pinterest

ML System Design · Recommendation Systems

Last reported Jul 2025

Design a low-latency RAG system

Companies: OpenAI

Embeddings & Vector Search · ML System Design · Retrieval-Augmented Generation

Last reported Jul 2025

Design a prompt processing backend

Companies: Anthropic

Job Scheduling & Workflows · Messaging & Event-Driven

Last reported Jul 2025

Design an ML search system with RAG

Companies: OpenAI

Retrieval-Augmented Generation · Search Relevance

Last reported Jul 2025

Design an Offline Batch Inference Service

Scope: - User interaction with this service - Sharding of Data - Resource Allocation - How does orchestration work - How does User know the…

Companies: DoorDash

Last reported Jul 2025

Design a prohibited medicine ads detection system

Design a machine learning system for Facebook's Ads platform that can automatically detect and block medicine advertisements to comply with new policy restrictions. The system…

Companies: Meta

Last reported Jun 2025

This inference pipeline is slow. Explain how you would debug it.

This was for an infra rather than modeling or research role.

Companies: Anthropic

Last reported Jun 2025

Design LLM search handling long token inputs

Companies: OpenAI

LLM Applications · Retrieval-Augmented Generation

Last reported Apr 2025

Design a system to predict which users will attend Facebook events in the real-world?

Events can be private with an invite list (e.g., birthday dinner) or public with no invite list (e.g., concert), each having a page showing details…

Companies: Meta

Last reported Mar 2025

What would you do to avoid underfitting and what would you do to avoid overfitting?

Companies: Oracle

Last reported Jan 2025

Implement K-Means Clustering Algorithm

Implement K-means clustering algorithm to group data from a dataframe or database

Companies: Google

Last reported Jan 2025

Design a Bot Post Detection ML Pipeline

Design a machine learning pipeline to detect bot-generated posts.

Companies: Meta

Last reported Nov 2024

Design a People You May Know Service

Design a service that suggests people a user may know based on their connections, interests, and other relevant data.

Companies: Meta

Last reported Sep 2024