Ramon is a research engineer and educator working at the intersection of AI and robotics at Menlo Labs. Currently, he is helping build the brain of a robot, a C++ tool to help bring different AI models into robots. Before that, he worked as a product developer and researcher, creating custom data tools, running workshops and developing training programs for clients in various industries. He has participated in several conferences and meetup events including PyCon, SciPy, PyData, MLOps World, and ODSC. In his free time, you will most likely find him traveling to a new place, mountain biking, or both.
Your roomba can't philosophize about the nature of dust, and your washing machine won't debug your code while spinning your clothes - not because they lack ambition, but because running AI models on constrained hardware has traditionally meant sacrificing either performance or memory - usually both. Cortex.cpp is an open-source engine to run AI models on everything from Raspberry Pis to industrial robots without breaking the bank. This talk goes over how AI models work on different hardware from a C++ perspective, different ways of using Python from within C++ and vice-versa, and how to enable near-metal performance through aggressive […]