44 posts
AISeptember 15, 2026by Formation
Long-context capacity is bounded by the KV cache: every resident token consumes finite GPU memory. Learn how to estimate the concurrency ceiling and monitor the latency signals that reveal cache pressure.
AISeptember 15, 2026by Formation
Streamed LLM responses need separate targets for time to first token and time per output token. Learn how workload shape, batching, deadlines, and cost determine the right SLOs.
AISeptember 14, 2026by Formation
LLM inference splits into compute-heavy prefill and memory-bandwidth-sensitive decode. Learn why batching helps, how long prompts disrupt streaming, and which latency metrics to measure.
Interview PreparationSeptember 10, 2026by Formation
In a vector database system design interview, focus on chunk policy, metadata, filtered search, and rebuild strategy—not just the store you name.
AISeptember 9, 2026by Formation
Learn how to design a RAG system for interviews by separating retrieval from generation, with distinct freshness, latency, failure, and quality decisions.
Interview PreparationAugust 26, 2026by Formation
When an AI assistant can write working code in seconds, interviewers stop testing typing speed and start testing whether you can clarify requirements, own the design, and verify what the model produced.
Interview PreparationAugust 25, 2026by Formation
When interviewers ask you to design an AI-powered feature, they're testing system design judgment, not ML knowledge — this post shows how to treat the model as an unreliable dependency and reason about its latency, cost, and failure modes.
AIJuly 28, 2026
AI can speed up system design interview prep and create a false sense of readiness. Here's how to use it to sharpen your reasoning while keeping the thinking yours.
Job HuntJuly 21, 2026by Formation
A practical guide to using AI for software engineering interview prep, from behavioral answers to system design, without losing the details that make you credible.
