Skip to content

Explore

Questions Companies Concepts Guides Sign in

How it works Questions Companies Concepts Guides Pricing Sample scorecard

Interview questions

Find a company or topic. Read the sources, then practice.

Coding study plans Companies Design mock

Loading the question library…

Practice system design interviews out loud with an AI interviewer, a shared whiteboard and a scorecard for your level.

How it works Questions Concepts Questions by company Comparisons Technologies Guides Cheat sheet Sample scorecard FAQ Use it as an app Sign in Pricing About and how we write Terms and guidelines Privacy Policy Contact

© 2026 SysRound. SysRound is an AI practice tool. The AI interviewer and the AI feedback can be wrong. Use it for your own practice, not to hire people.

Search questions

CompanyType a name, then choose a company from the suggestions.

Question type

Difficulty

TopicType a topic, then choose one from the suggestions.

23 questions

Showing 1–23

System designMedium
Design a Model Inference API and Optimize Its GPU Usage
Companies: Anthropic
LLM Inference & Serving · System Design · System Design Fundamentals
Last reported Oct 2026
Open workspace
System designHard
Design a Batched LLM Inference Service Assuming Each Batch Takes 100 ms
Companies: Anthropic
LLM Inference & Serving · System Design · System Design Fundamentals
Last reported Oct 2026
Open workspace
System designHard
Design a Chat Assistant Inference Service: Streaming, Free-Tier Limits, GPU Scheduling
Companies: OpenAI
LLM Inference & Serving · Rate Limiting · System Design

Interview questions by company and topic | SysRound

Last reported Sep 2026

ML system designMedium

Trace an LLM Request Through a Paged-KV Inference Engine

Companies: AMD

LLM Inference & Serving · ML System Design

Last reported Sep 2026

ML system designHard

Design an LLM Inference Serving System

Companies: Baseten

LLM Inference & Serving · ML System Design

Last reported Jul 2026

ML system designMedium

Design a Low-Latency GPU Inference Service

Companies: Anthropic

LLM Inference & Serving · ML System Design · System Design Fundamentals

Last reported Jul 2026

System designHard

Design a Dynamically Batched Inference API

Companies: Anthropic

LLM Inference & Serving · System Design

Last reported Jul 2026

ML system designHard

Design an LLM-Based Coding Assistant

Companies: Meta

LLM Inference & Serving · ML System Design

Last reported Jun 2026

ML system designHard

Optimize LLM Training and Serving

Companies: Adobe

LLM Inference & Serving · ML System Design · Transformers & Attention

Last reported May 2026

System designMedium

Dynamic Batching for Synchronous Model Inference on One GPU with a 100-Input Cap

Companies: Anthropic

LLM Inference & Serving · System Design · Technical Tradeoffs for PMs

Last reported Apr 2026

ML system designMedium

Design GPU inference request batching

Companies: Anthropic

LLM Inference & Serving · ML System Design

Last reported Mar 2026

System designMedium

Design a ChatGPT-like serving system

Companies: Microsoft

LLM Inference & Serving · System Design

Last reported Mar 2026

ML system designHard

Design a high-concurrency LLM inference service

Companies: Anthropic

LLM Inference & Serving

Last reported Feb 2026

Practical engineeringMedium

Explain KV cache in Transformer inference

Companies: OpenAI

LLM Inference & Serving · Transformers & Attention

Last reported Jan 2026

ML system designHard

Design an inference routing and scheduling layer

Companies: Anthropic

Caching · LLM Inference & Serving · ML System Design

Last reported Sep 2025

ML system designHard

Implement KV cache for inference

Companies: Applied Intuition

LLM Inference & Serving · ML System Design · Transformers & Attention

Last reported Sep 2025

ML system designHard

Review an inference API design for scale

Companies: Anthropic

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

Last reported Sep 2025

ML system designHard

Design a GPU inference API

Companies: Anthropic

GPU Infrastructure · LLM Inference & Serving · ML System Design

Last reported Aug 2025

Machine learningMedium

Explain FlashAttention, KV cache, and RoPE

Companies: TikTok

LLM Inference & Serving · Transformers & Attention

Machine learningMedium

Explain Top-k and Top-p Decoding

Companies: Cohere

LLM Inference & Serving

Machine learningHard

Explain Transformer Attention Fundamentals

Companies: Adobe

LLM Inference & Serving · Transformers & Attention

Machine learningMedium

Transformer Complexity, Inference Optimization, GQA and FlashAttention

Companies: LinkedIn

LLM Inference & Serving · Transformers & Attention

Machine learningMedium

Why do transformers struggle with long context?

Companies: Dandy

LLM Inference & Serving · Transformers & Attention