Hey there. I'm
Building high-performance inference for the intelligent edge.
About
I am interested in the architectural challenges of on-device machine learning and the deployment of intelligent IoT systems.
01WHAT
My interest lies at the intersection of machine learning and local compute. I focus on the practical constraints of edge deployment: minimizing latency, optimizing power, and maximizing throughput on specialized silicon.
02WHY
As neural processing units (NPUs) become increasingly capable, they enable a new class of local inference. The next major shift in AI won’t happen on a remote server, but on the edge platforms we use every day.