Interview with Sheng Ying: Leaving xAI to Found RadixArk for SGLang
xiaosun86 · x · 2026-08-05
This podcast features an in-depth interview with Sheng Ying, the creator of the open-source inference engine SGLang and former head of inference at xAI, discussing her academic journey, AI Infra philosophy, and entrepreneurial path.
After attending the SJTU ACM class and exploring research directions from formal verification to AI Infra at Columbia and Stanford, Sheng views AI infrastructure as a "romantic relationship" with aesthetic value. Joining xAI early on, she helped build production-grade inference systems with significant freedom and support.
However, as the SGLang community expanded rapidly, maintaining the project with part-time developers became unsustainable. To ensure SGLang's continued growth, Sheng decided to leave xAI and founded RadixArk, aiming to build a future where humanity coexists safely with powerful AI.
Related event: Former xAI Inference Lead Sheng Ying Leaves to Found RadixArk(3 posts)→
More from Companies & People
- BBVA Launches Sierra's Horizon Agent in 30 Days to Serve Customers — saranormous · 2026-08-05
- Conviction Launches Embed v7 Founder Program, Focuses on AI and Robotics — saranormous · 2026-08-05
- Forrester: An AI Model Is Not a Business Model, Enter the Platform Era — mgualtieri · 2026-08-05
- Visa's AI-Driven Restructuring Eliminates 320 Bay Area Jobs, Including 6 VPs — sfgate · 2026-08-05
- xAI Announces Fourth Data Center with 220,000 GB300 GPUs — chrisgrayson · 2026-08-05
- Airtable Acquired for $2.6B, Spins Out AI Agent Business Hyperagent — rickasaurus · 2026-08-05