InterviewStack.io LogoInterviewStack.io

Performance Optimization and Latency Engineering Questions

Covers systematic approaches to measuring and improving system performance and latency at architecture and code levels. Topics include profiling and tracing to find where time is actually spent, forming and testing hypotheses, optimizing critical paths, and validating improvements with measurable metrics. Candidates should be able to distinguish central processing unit bound work from input output bound work, analyze latency versus throughput trade offs, evaluate where caching and content delivery networks help or hurt, recognize database and network constraints, and propose strategies such as query optimization, asynchronous processing patterns, resource pooling, and load balancing. Also includes performance testing methodologies, reasoning about trade offs and risks, and describing end to end optimisation projects and their business impact.

MediumTechnical
63 practiced
Explain how you would use eBPF (BPFtrace/BCC/IO Visor tools) to profile latency and network stack issues in a production Linux cluster with minimal overhead. Which probes would you attach (kprobes/uprobes/tracepoints), which metrics would you collect, and how would you correlate kernel-level signals with application-level traces?
EasyTechnical
55 practiced
You are defining SLOs for an HTTP JSON API used by a billing product. Describe how you would pick SLO targets and error budgets, which latency and availability metrics to use, and how to translate business impact (e.g., lost revenue, customer churn) into SLO thresholds. Explain how error budgets should influence release cadence and incident response playbooks.
EasyTechnical
51 practiced
When would you use a CDN versus an application-level cache (e.g., Redis) to reduce latency? Explain scenarios where caching helps, where caching can hurt (cache stampedes, stale data), and which metrics (e.g., cache-hit ratio, origin latency, TTL distribution) you would instrument to validate a caching decision.
HardTechnical
59 practiced
Implement a memory-efficient sliding-window rate limiter in Java that supports per-key limits and high concurrency. Use a sharded approach based on fixed time shards (e.g., N sub-windows per sliding window). Provide a public API, explain thread-safety approach (ConcurrentHashMap, atomic counters), TTL eviction for inactive keys, and discuss memory/time trade-offs and scaling across instances.
MediumSystem Design
60 practiced
Design a low-latency, read-heavy key-value store to serve 10,000 RPS reads with p99 latency under 5ms. Include choices for caching, replication, read paths, consistency models, data partitioning, hot-key handling, and failover. State assumptions about hardware and network and sketch a monitoring plan to validate SLOs.

Unlock Full Question Bank

Get access to hundreds of Performance Optimization and Latency Engineering interview questions and detailed answers.

Sign in to Continue

Join thousands of developers preparing for their dream job.