I enjoy documenting my ideas, experiences, and learnings, and over time, I’ve found that sharing them can be helpful to others. This inspired me to turn my notes into articles on my website, covering everything from foundational concepts and emerging trends in my field to interesting topics, personal reflections, technical insights, and lessons learned along the way . . .

Blogs

Chunked Prefill: Stopping One Long Prompt From Freezing Everyone Else

Sep 25, 2026
LLM Inference Chunked Prefill Scheduling

Prefix Caching: Reusing the Work You’ve Already Paid For With RadixAttention

Sep 23, 2026
LLM Inference Prefix Caching RadixAttention

The Scheduler: Backpressure, Timeouts, and Knowing When to Say No

Sep 13, 2026
LLM Inference Scheduling Backpressure

Continuous Batching: Getting More LLM Throughput From the Same GPU

Sep 09, 2026
LLM Inference Continuous Batching Throughput

KV Cache on Apple Silicon: Why Memory Fragments and How PagedAttention Helps

Sep 05, 2026
LLM Inference KV Cache Memory Management

From Naive Decode to KV Cache: Why LLM Serving Gets Faster With One Idea

Sep 03, 2026
LLM Inference KV Cache Inference Optimization

System Design 05: Designing an AI Coding Agent Platform like Claude Code / Cursor

Aug 19, 2026
AI System Design Agentic AI

System Design 04: Designing an LLM Chat Product With Memory and Context Management

Aug 11, 2026
System Design AI LLM

System Design 03: Designing a RAG Pipeline for 10 Million Documents With Near-Zero Hallucination

Aug 03, 2026
AI System Design RAG

System Design 02: Designing a RAG-based Q&A System Over Company Docs

Jul 29, 2026
AI System Design RAG

System Design 01: Designing a Delivery app with AI features for salesmen

Jul 26, 2026
System Design SWE AI

AWS Nuke - The AWS Resources Destroyer

May 02, 2026
AWS Tooling Infrastructure

UV & Modern Python Dependency Management

Feb 24, 2026
Tooling Package Management

Kubernetes Project Workflow - Commands & Mental Model

Feb 07, 2026
MLOps Cloud Native

Dynamic Programming Patterns - Non Adjacent Selection DP

Oct 11, 2025
Dynamic Programming Algorithms

Open Source Contribution - Beginner's Guide

Jul 31, 2025
Open Source SWE

An Introduction to Self Supervised Learning (SSL)

Nov 19, 2023
Representation Learning