Llm-ops - TechnoScripts

llm-ops

Running large language models in practice: prompts, tokens, context windows, cost, latency, and deployment patterns for real LLM applications.

RAG System Design: The LLM Interview Whiteboard Round

RAG system design, short for Retrieval-Augmented Generation, is the GenAI whiteboard round where an interviewer says “design ChatPDF for an enterprise” and then watches how you think for forty-five minutes, not what you can draw. This post walks that round end to end: an eight-layer framework, two fully worked designs, the follow-up gauntlet on ACLs, freshness, and scale, and a mock transcript with the rubric, every number computed with real code. “They grade the numbers you defend, not the boxes ... Read More

LLM and GenAI Interview Questions: 40-Question Checkpoint

GenAI screens do not chase whichever model launched last week; they recycle a fixed set of durable ideas in slightly different words. The LLM interview questions in this checkpoint cover that set, forty in all, grouped the way real screens group them, each with a short spoken-style answer, runnable code for the numbers people fumble, and a link to the deep-dive post that teaches it in full. Then you score yourself, get a revisit list built from exactly what you ... Read More

LLM Serving: Ollama Locally, vLLM in Production

Renting tokens from an API is easy; the bill and the data both leave the building. LLM serving is the craft of running an open Large Language Model yourself, fast enough for real users, and this post walks both ends of it with tested Python: Ollama on your laptop for development, vLLM in production, plus the KV-cache math that decides how many users one Graphics Processing Unit (GPU) can actually hold. “The cheapest, fastest, and most reliable components are those ... Read More