Questions about Jae L.
What is Jae L.?
Jae L. is an individual contributor focused on building GPU kernels and machine learning systems. The work spans multiple hardware architectures, including NVIDIA Blackwell with NVFP4, AMD MI355X with MXFP4, and Apple silicon through a custom MoE Metal kernel. They contribute to open-source projects such as the SGLang MLX backend, where they lead optimization efforts for MoE performance on Apple hardware.
What writing or documentation methods are used?
The website says the work involves cross-substrate development across NVIDIA, AMD, and Apple silicon. The contract nobody wrote down is a notable piece of writing that discusses four bugs in one month. The Zettelkasten organization method is used for technical notes and reading.
What upcoming events are associated with this name?
The McSwain Theatre Showcase featuring Jae L. & Crossover is scheduled for 2026-11-10. Christmas magic is in the air and the event is celebrating Dec. 19 at 7 p.m. This event is located in the McSwain Theatre.
Where can the website and contact information be found?
The website domain is jaeb.dev. The website is https://jaeb.dev. Contact can be found via GitHub, LinkedIn, X, or Email links on the site.
Does Jae L. have reviews on Trustburn?
Jae L. has no reviews on Trustburn yet. Anyone who has used it can write the first review on its Trustburn page.
AI-generated from reviews on this page. Verify anything important with the company directly.
News
No news yet. This is where the business shares its own updates and press.
Photos
No photos yet. Photos shared by reviewers will show up here.
Widgets
Get the widget for your site →About Jae L.
Jae L. is an individual contributor focused on building GPU kernels and machine learning systems. The work spans multiple hardware architectures, including NVIDIA Blackwell with NVFP4, AMD MI355X with MXFP4, and Apple silicon through a custom MoE Metal kernel. They contribute to open-source projects such as the SGLang MLX backend, where they lead optimization efforts for MoE performance on Apple hardware. Additional projects include an AMD MXFP4 matmul kernel and a small serverless GPU inference engine for consumer hardware. They also maintain a personal blog with technical notes organized as a Zettelkasten.
- Website
- jaeb.dev