Partners
Compiling models to megakernels
Standard GPU inference wastes time on kernel launch overhead, uneven work distribution, and memory access delays between operations. Luminal's compiler fuses entire neural network models into single GPU kernels — megakernels — using a dynamic global instruction queue that schedules work across streaming multiprocessors at runtime, eliminating the gaps that conventional approaches leave behind.
Read the postWhat is this?
These organizations are partners with 3Blue1Brown seeking to hire technically curious people like you. If this channel were a university, think of this as the campus career fair where you can find aligned opportunities. Explore the pages here to learn what makes each team unique.
Want to be featured here?
If your organization would like to partner with us, please send an inquiry to talent@3blue1brown.com and we can explore whether it's a good fit. The main thing we care about is whether members of your technical team genuinely love working there.
Find a job here?
If you find a job through this page, we'd love to hear your story!
Let us know via the general contact form.
