Summary
Kory Watson is a Staff Engineer and manager in Seattle with 11 years of experience specializing in machine learning deployment, compilers, and performance optimization for edge devices. He has led the creation and operation of Qualcomm’s AI Hub—a developer-facing model repository, benchmarking suite, and deployment workbench—bringing SOTA models like diffusion and LLMs to mobile hardware. His background spans founding-stage work at Tetra AI (acquired by Qualcomm) where he delivered 2–10x real-world latency and power wins, plus compiler and runtime contributions from CoreML at Apple. Kory blends hands-on systems and compiler expertise (operator fusion, quantization, ML graph compilation) with product-facing API and service design to make complex ML stacks usable for developers. He has a track record of identifying regressions via continual benchmarking and shipping fixes that materially reduce latency across many graphs. Beyond engineering, he teaches and documents low-level systems concepts, reflecting a rare combination of deep tooling knowledge and developer empathy.
11 years of coding experience
8 years of employment as a software developer
Bachelor’s Degree, Computer Engineering, Bachelor’s Degree, Computer Engineering at University of Washington
English, Spanish