Problems / LLM serving, medium

PII redaction on the hot path

Every prompt is scanned by a PII redactor with 2 vCPUs and 10 ms of CPU per prompt, at 400 requests a second.

Solve it in the labTake it as a mock interview

Unlock it once for 15 credits; everything inside it is free (runs, changes, Submit, results, hints). Sign in with Google to start; new accounts get free credits.

Your goals

Success ≥ 99%, p99 ≤ 5 s.

Test cases

Like a coding problem, a solution has to pass every case, not just the one it was built for. Submit in the lab runs all 4; 1 of them are hidden until then.

  1. As given. The problem’s own traffic, scheduled failures and seed.
  2. A slow dependency. The main data store or model answers twice as slowly for part of the run.
  3. A server dies. One replica of the service with the most replicas is killed for part of the run.

The traffic

400 requests a second for 30 seconds: 100% request (reads).

The system

What each component does in this design, and what calls it. The simulator mimics each one from these settings.

ComponentIts job hereSettings
Load balancerLoad balancerTraffic enters here.Calls AI app.Layer 4 balancers route by IP and port; layer 7 balancers read HTTP and can route by path or header.–
AI appApp serviceLoad balancer forwards to it.Calls PII redactor, GPU serving pool.Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s.3 replicas × 500 slots · timeout 30 s
PII redactorPII redactorAI app calls it.Redacting personal data before it reaches a model or a log reduces privacy and compliance risk.400 slots
GPU serving poolSelf-hosted serving poolAI app calls it.GPU servers batch requests together; throughput rises with batch size until memory runs out.2000 slots

More llm serving problems