Rik Kisnah - Blog
Posts
About
Publications
Resume
Teach
MCP
github
linkedin
#LLM
Design a Token Usage and Limits Service
Jun 16, 2026
Design a Token Usage and Limits Service
Chat Is the Product. API Is the Contract. CLI Agents Are the Harness.
Apr 26, 2026
Chat Is the Product. API Is the Contract. CLI Agents Are the Harness.
A Short History of AI: From Greek Myths to Large Language Models
Mar 28, 2026
A Short History of AI: From Greek Myths to Large Language Models
Attention Is All You Need — And All You Need to Know: An Infrastructure Engineer's Guide to the Paper That Built Your GPU Cluster
Feb 28, 2026
Attention Is All You Need — And All You Need to Know: An Infrastructure Engineer's Guide to the Paper That Built Your GPU Cluster
How Large Language Models Actually Work
Nov 30, 2025
How Large Language Models Actually Work
Design an Inference API
Nov 11, 2025
Design an Inference API
Continuous Batching for Inference
Apr 15, 2025
Continuous Batching for Inference
Size the KV Cache
Feb 18, 2025
Size the KV Cache