High-Performance ML & Computer Vision · Heterogeneous AI Systems
I'm a machine learning engineer focused on computer vision and inference at scale — taking models from research code to production across GPUs, edge accelerators, and everything in between. I care about the parts most people skip: latency budgets, memory footprints, and pipelines that keep working after the demo ends.
Outside of shipping, I write about deployment tradeoffs and heterogeneous compute on the blog below.
Notes on Andrew Ng's four AI engineering skills, and the tension between two of them.
Building an engineering contract that makes the model a replaceable part — constraints, handoff packets, enforced boundaries, and what delegation really costs.
A practical workflow for project constitutions, feature specs, implementation, validation, replanning, and reusable coding-agent automation.
Happy to talk about computer vision and ML infrastructure.