How do I approach ML System Design interview questions?

ML System Design questions require understanding of core concepts and practice. PracHub provides solutions with explanations to help you master ml system design interviews.

What difficulty level is this interview question?

This is a medium difficulty ML System Design question, commonly asked during Technical Screen rounds at OpenAI.

What role is this question designed for?

This question is commonly asked for Software Engineer candidates at OpenAI during technical interviews.

Design AI chat bot system

Last updated: Mar 29, 2026

Quick Overview

This question evaluates understanding of ML system design and front-end–centric architectures, focusing on browser-only state management, streaming LLM responses, SPA lifecycle constraints, stateless relay integration, and credential/security considerations.

OpenAI

Aug 4, 2025, 10:55 AM

Software Engineer

Technical Screen

ML System Design

System Design: In-Browser AI Chat With Streaming

Requirements

Design a web-based AI chatbot system that satisfies all of the following:

User messages and full conversation history are stored only in the browser (no backend database or server-side persistence).
Bot responses are streamed to the user token-by-token (or chunk-by-chunk).
Refreshing the page starts a new conversation (no history survives a reload).
Handle user credential and security considerations.

Assume a typical SPA front end and that you may use a stateless backend relay to call an external LLM provider, but you must not persist user messages server-side.

Solution

Show

Comments (0)

Loading comments...

Browse More Questions

More ML System Design•More OpenAI•More Software Engineer•OpenAI Software Engineer•OpenAI ML System Design•Software Engineer ML System Design