GPU Scheduling at Scale: How Modern Systems Stop Fighting Over Silicon
GPUs are no longer exotic, but scheduling them well is still hard. This post walks through the policies, primitives, and production patterns that decide who gets the silicon.
Distributed-Systems
AI Infrastructure Hiring Is Converging: What It Means for Engineers
AI infrastructure hiring is converging into a single, hybrid discipline that blends platform engineering, MLOps, and distributed systems. This post breaks down what skills are merging, what the new job descriptions look like, and how engineers can position themselves.
Inference Is Becoming a Distributed-Systems Problem
Once a model fits on one accelerator, inference is mostly GEMMs and kv cache lookups. Once it doesn’t, you inherit every problem distributed systems has spent thirty years failing to solve.
AI Infrastructure Is Becoming the Next Major Infrastructure Discipline
AI infrastructure is crystallizing into a distinct discipline — one with its own hardware, scheduling, and observability stack. This post breaks down the layers, the patterns in production, and the skills engineers need to build it.
Optimizing Redis with Client-Side Caching and the RESP3 Protocol
A practical look at how the RESP3 protocol and client-side caching let Redis clients invalidate entries locally, eliminating round trips and shaving milliseconds off tail latency.