← Coding for Infra / 36

hardNew

Implement a thread-safe in-memory KV store with snapshot transactions and TTL

Define when expiry is observed, stage writes privately, and reject a conflicting commit. Use a small conservative protocol before optimizing concurrency.

Updated Sep 2026 · Learn how AI infrastructure works through explanations, worked examples and diagrams, then practise applying it to interview questions.

Define when expiry is observed, stage writes privately, and reject a conflicting commit. Use a small conservative protocol before optimizing concurrency.

The full answer is part of Premium. A free account includes more answers in each topic, but does not unlock this one.

20 answers per topic instead of 10, plus saved progress and bookmarks · no cardor unlock all 303 remaining answers · ₹2,000 / $25

The concepts behind this question

Use these concept explanations to review the ideas behind this question.

🧮 Napkin Math & Capacity

KV Cache SizingDerive cache payload from the stored attention state, then account for mixed sequence lengths, block allocation and per-device limits. Worked examples distinguish exact bytes from deployable capacity.

💻 Coding for Infra🔒 Premium

Concurrency in Python, Go and C++Concurrency primitives coordinate overlapping work and shared state. Choose threads, processes or asynchronous tasks from the runtime and the work they must perform.

💻 Coding for Infra

The GPU Credit Scheduler PatternA credit scheduler admits jobs without overspending an account’s balance. Clear state transitions make priority, cancellation and refunds easier to implement correctly.

💻 Coding for InfraSign in

Rate-Limiting AlgorithmsRate limiters control how much work a caller may submit over time. Token buckets, queues and sliding windows allow different burst and waiting behavior.

Explore the full curriculum →

UP NEXT ON YOUR JOURNEY

Next in this trackImplement sliding-window attention without confusing token positions with ring-buffer slots Next in this trackImplement symmetric INT8 quantization and prove where the reconstruction-error bound applies Closest to this topicImplement a bounded request log with timers that remain correct under concurrency

DISCUSSION · 0

No comments yet — be the first to share your approach.