Intelligent Systems Engineer specializing in Robotics & AI. Expertise in ML/DL, Python/C++, LLMs, RAG, and end-to-end intelligent systems development. Passionate about solving complex problems with AI.
Nothing here yet.
Nov 24, 2025 · 4 min read · Why MoE Can Have Many FFNs Yet Use Less Memory & Compute Large Language Models (LLMs) like GPT-OSS, Mixtral, and DeepSeek-V3/R1 use Mixture-of-Experts (MoE) layers to massively expand model capacity without increasing inference cost. But the mechanis...
Join discussion
Aug 20, 2025 · 40 min read · Note: This document provides structured and elaboratively encoded study notes designed for deep conceptual understanding, long-term retention, and easy navigation. It is just my personal rewritten version of concepts I’ve studied from Chip Huyen’s bo...
Join discussion
Aug 1, 2025 · 47 min read · Welcome to a deep dive into one of the most critical and fascinating areas of AI Engineering: Inference Optimization. While building powerful models is one part of the equation, making them run efficiently—faster, cheaper, and at scale—is what makes ...
Join discussion
Jul 31, 2025 · 5 min read · The AI landscape is evolving rapidly, and while model architecture and compute power are critical, the true differentiator is increasingly becoming the data. As companies move away from building models from scratch, the focus shifts to dataset engine...
Join discussion