I’m thrilled to announce that I’ve joined the team at Edge Impulse, in the role of Founding TinyML Engineer.

Edge Impulse are building the developer toolchain for TinyML. Their vision is that every engineer should be able to train and deploy embedded machine learning models, without needing a background in machine learning or data science.

When I saw Zach demo the Edge Impulse product at one of our TinyML meetups last year, I was blown away. While platforms like TensorFlow make it possible to do incredible things on-device, they are low-level tools that require hard-won domain expertise to work with. Edge Impulse makes these powers accessible to every single developer, unlocking the creative potential of millions of people.

It’s been a huge decision to walk away from Google, and I’m deeply grateful for the time I’ve spent there and the brilliant people I’ve been fortunate enough to work with. I’m especially indebted to Pete Warden and his TensorFlow Lite for Microcontrollers team, who first introduced me to the idea of deep learning on embedded devices. It’s likely that 2020 will be the decade of TinyML, and Pete’s team has a lot to do with it.

Edge Impulse is launching very soon, and I’m excited to be jumping into the fray as their first full-time hire! You can see a sneak peak of the product here, and I encourage you to sign up for the developer preview to be notified when we launch. We’ll be working hard to make this a tool you love to use, and I can’t wait to hear your thoughts.