Cracking ML System Design Interviews — Design a Search and Ranking System

<!-- SC_OFF --><div class="md"><p>Been working with a few teams integrating RAG into internal tools, support bots, document Q&amp;A, contract search, and I keep running into the

<!-- SC_OFF --><div class="md"><p>Most people are still manually wrestling with vector databases and embedding models. If you're building for enterprise, Vertex AI Search is doing

<!-- SC_OFF --><div class="md"><p>AI skills and agents feel like the units you can build real things with. Skills are portable, composable, they travel with the model. One skill

<!-- SC_OFF --><div class="md"><p>I've been working on MDA (Modular Dynamic Architecture), an online associative memory system for LLMs. Here's what I learned building it.</p>

<!-- SC_OFF --><div class="md"><p>AI fluency is now baseline in interviews, but Robert Half shows why judgment and critical thinking matter more as AI makes hiring slower and more

<!-- SC_OFF --><div class="md"><p>I wrote this after thinking through what happens when advertising enters conversational AI.</p> <p>Search engines ranked pages.<br /> Social

<!-- SC_OFF --><div class="md"><p>We spent the last year building a code indexing system and tried pretty much every retrieval approach along the way. Sharing what actually worked

<p><strong>Here's a dirty secret of search: "the closest match" and "the most useful result" are not the same thing. Return the mathematically nearest document and you'll often