Taught by practising kernel engineers

Go deeper than any other course will take you.

Kernel engineering, embedded systems and AI compute infrastructure. 115 courses across 16 tracks — live and hands-on, in eight cities or online from anywhere.

115courses
16tracks
8cities
14max cohort
ring 3 — userspace ring 1 ring 0
Most training stops three rings out.

Sixteen tracks

From processor architecture to thousand-node HPC. Pick a track to see its modules.

Taught by people who do this work

Every course is delivered by a practising engineer whose day job is the material — with backgrounds across Wind River, Qualcomm, Amazon Robotics, Graphcore and Spire, and kernel work shipping in production today.

That is the whole proposition. Vendor training is taught from a script by professional instructors. This is taught by people who do the job, reading real source on real hardware.

The instructors How we teach
35 / 20 / 45principles, guided investigation, engineering studio
14maximum cohort size
Real hardwareboards and GPU nodes, not slides
Adaptedto your kernel version and stack

Train your whole team at once

Any course can run privately — on-site at your offices anywhere in the world, or live online for a distributed team. Scheduled around your release calendar, with labs adapted to your hardware.

Request a proposal