xAI inference and kernel engineer departs, citing SGLang, attention kernels and C++ inference stack rewrite
HanchungLee · x · 2026-11-06
Hanchung Lee announced he has left xAI's SpaceX infrastructure side, thanking colleagues across the inference, kernel, supercompute, foundation and Starlink teams.
He highlighted his technical contributions: work on SGLang, attention kernel optimization, fast 0-KL for large-scale RL, and rewriting the inference stack in C++ from first principles. He also thanked Elon Musk for assembling the team.
The tweet's visible text is an unrelated restaurant review of Imperial Treasure in Palo Alto (3/5).
More from Companies & People
- ETH Zurich releases full open-source VLSI course: 12 lectures plus OpenROAD-based exercises — Obijuan_cube · 2026-11-06
- Mystery OpenAI gift card with giant smiling face shows up at AI researcher's doorstep — Yuchenj_UW · 2026-11-06
- Analyst: "Anthropic is after our data" is becoming the go-to grifter pitch — teortaxesTex · 2026-11-06
- Physical AI meetup in India: 4 robotics founders on real factory deployments and eval loops — carrycooldude · 2026-11-06
- Boom founder: only ~5 of 165 staff work on supersonic jet as energy comes first — dunkhippo33 · 2026-11-06
- Design teams aren't being cut for lack of work—the bar has fundamentally risen in the AI era — LadyAshBorg · 2026-11-06