Skip to content

Details

Live online · October 12–December 7, 2026

Course details and enrollment: https://maven.com/rajat-dandekar/kernel-engineering

Discount code: AIPERF15 for 15% off!

Join Vizuara’s live Kernel Engineering cohort, run in partnership with Crusoe. Learn how GPU kernels work from first principles, then write, profile, and optimize them through practical coding sessions.

The course covers parallelism, the roofline model, CUDA, GPU memory, matrix multiplication, tensor cores, and attention kernels, building toward modern tools and an engineering capstone. Recordings and code are included.

Designed for engineers comfortable with Python and basic PyTorch; no prior CUDA or C++ experience is required.

Preview the teaching
Explore the lecture slides and watch the associated YouTube lecture to get a feel for the teaching style and depth before enrolling.

Lecture slides — no login needed: https://kernel-cohort.vercel.app/lecture1/v1#s1

Associated YouTube lecture:
https://youtu.be/Nn5XlSwVlOw

You may also like