Story 007 - Making LLM Inference Faster Led Me Down the Performance Stack
Published:
From nvtop to NVIDIA Nsight: Going Beneath GPU Utilization.
⚔️ Engineering War Stories
An engineering logbook of the battles behind systems I've built—not just successful deployments, but also prototypes, failures, infrastructure work, debugging sessions, and performance optimizations that shaped how I think as an engineer.Story 006 - The Parallelism That Made Things Slower
Published:
I implemented concurrency on intuition. Then performance engineering made me question my life choices.
Story 005 - I Tried to Give My Job to a Machine
Published:
The QA Assignment That Made Me Design My Own Replacement
Story 004 - The MCP Detour That Taught Me Microservices
Published:
I was asked to implement MCP. I fell in love with microservices and it’s a toxic relationship.
Story 003 - When an OS patching broke production
Published:
A break-glass temporary recovery action to bring the service back online.
Story 002 - The Curious Case of Missing G5 Capacity
Published:
How do you keep a production chatbot alive when your required GPU hardware disappears?
Story 001 - First production deployment (feat. RHEL EC2)
Published:
Infrastructure vs. Platform: Setting Up a GPU for Production
Story 000 - Bootstrapping an AI Development Environment
Published:
The Chatbot That Earned Its Own GPU