Top 50
Topic roadmap
Updated weekly · Last refresh Sep 13

Top 50 latency Interview Questions

The most frequently asked latency questions across all roles and companies, ranked by real interview frequency. Updated daily.

50questions
~7htotal time
270companies covered
Track your progressSign up free to work through all 50 questions and resume where you left off.
Start practicing free →
1
CodingStart here. 4 questions · ~35 min
Rolling Latency Percentiles and AlertsHard
Practice
Recently asked

Compute rolling p50 and p95 latency with a sorted sliding window and flag sudden generation spikes.

latencyanomaly detectionAnthropic
K-th Smallest Latency ValueMedium
Practice

Find the k-th smallest TikTok Shop server latency using a max-heap with O(n log k) time.

latencyArraysSortingTikTok Shop
ISR Latency and Interrupt HandlingMedium

Explain what an ISR does, how interrupt latency arises, and how to reduce it in embedded systems.

latencyEmbedded SystemsinterruptsNokiaInfineon TechnologiesDiversified Services Network
More Coding questions with a free account

Sign up to see every question

Create a free account to unlock this list and practice real interview questions.

Get my prep plan
2
System Design39 questions · ~342 min
Design a Low Latency Inference PlatformHard
Recently asked

Design a low latency ML inference platform for high-frequency online predictions with strict response times and evolving model features.

high-frequency requestslatencysystem architectureAnthropicSScaled CognitionPPrima
Design an Enterprise RAG PipelineHard
Recently asked

Design an enterprise RAG system that balances retrieval quality, grounded answers, and low latency over frequently changing internal data.

latencyRAG pipelinesAccuracyWorkdayLtimindtreeHewlett Packard Enterprise | HPE
Design a Low-Latency Ranking ServiceMedium
Recently asked

Design a production ranking service that balances model accuracy with latency and throughput under large-scale traffic.

latencythroughputAccuracyChenegaPlaystation NetworkENGIE
Serving Multiple Fine-Tuned LLMsHard

Design a low-latency, cost-aware serving platform for multiple fine-tuned LLMs under variable traffic.

gpu hardwarelatencyml inferenceGrafana LabsSandia National LaboratoriesClickUp
More System Design questions with a free account
3
Execution4 questions · ~35 min
More Execution questions with a free account
4
More topics3 questions · ~26 min
Design High-Throughput Event PipelineHard
Recently asked

Design a real-time event pipeline that can handle millions of events per second with sub-second latency.

data pipelineevent processinglatencyAlpacaKDA ConsultingAltimate.Ai
More questions with a free account
The finish line: interview-readyComplete all 50 questions to finish this plan.