Skip to content
Learning

Everything I've written, in one place

Articles on LLM systems, retrieval, AI security and backend engineering — written while learning them the hard way. Posts are pulled from Medium and refresh automatically.

Follow on Medium
Latest23 min read

LLM Inference Optimization: The Complete Guide to Serving Models Faster and Cheaper

From roofline math and KV cache budgets to quantization, speculative decoding, disaggregated serving and a hands-on vLLM tuning workflow. Training is a one-time…

  • artificial-intelligence
  • ai-cost-optimization
  • mlops
  • llm
  • inference-optimization
Read article
22 min read

Hybrid RAG: Why Your Retriever Needs Both Keywords and Vectors

An advanced, end-to-end guide to building retrieval that actually finds the right context: fusion math, rerankers, graph hybrids, code, and evaluation. The query…

  • rags
  • llm
  • vector-database
Read article
12 min read

Your AI Agent Just Deleted a Failing Test. Here’s an Architecture That Would Have Stopped It.

Vīthi: designing AI agents with a 2,000-year-old map of the mind Picture a coding agent with one goal: make CI green. It runs the test suite. One test fails,…

  • buddhism
  • software-architecture
  • ai-safety
Read article
4 min read

The Last Human-Driven Car Just Flew. Tesla Says AI Had Nothing to Do With It.

Elon Musk needed a live crowd to prove his flying Roadster wasn’t AI-generated. That’s the most revealing part of the whole story. On the night of October 15, 2026,…

  • future
  • technology
  • elon-musk
Read article
6 min read

What Is SAP? A Practical Guide to the World’s Biggest Business Software

From a five-person startup in 1972 to the backbone of global business, what SAP does, why it matters in 2026, and where it’s heading. What Is SAP? You have almost…

  • careers
  • digital-transformation
  • erp-software
Read article
15 min read

Stop Building RAG Pipelines for Documents That Fit in Context Cache-Augmented Generation is boring…

Stop Building RAG Pipelines for Documents That Fit in Context Cache-Augmented Generation is boring, unsexy, and beats your vector database on bounded corpora. You…

  • cag
  • llm
  • rags
Read article
6 min read

NVIDIA NeMo Guardrails: Building Safer, More Controllable LLM Applications

A practical guide to adding programmable safety rails to your LLM apps — with Colang examples, architecture breakdowns, and production tips. Why Guardrails? Large…

  • nvidia
  • ai-safety
  • machine-learning
Read article
7 min read

Setting Up OAuth in a Next.js App — The Right Way

A complete guide covering provider setup, domain verification, environment variables, and production-ready patterns. Why OAuth? Building your own authentication from…

Read article
9 min read

How to Use Gemma 4 to Manage Your Google Drive with AI

Build a conversational AI agent that lists, searches, uploads, and organizes your Google Drive files , all powered by Google’s brand-new open-source Gemma 4 model.…

  • llm
  • agentic-ai
  • google-gemma
Read article
5 min read

BF16 and INT8 Explained: How LLMs Fit Into Your GPU

A ground-up guide to the number formats that make large language models fast, small, and practical , no prior knowledge needed. The Problem Computers Have With…

  • llm
  • model-optimization
  • machine-learning
Read article