AI Infrastructure Performance & Modeling Lead

Renice AI is seeking a Performance Lead to drive architecture decisions for AI inference workloads across the full system stack in Mountain View, CA. You will build modeling frameworks, analyze tradeoffs across compute, memory, networking, and storage, and translate results into actionable guidance for internal teams and hardware partners.

This role leads a small team of engineers, collaborates with ML, systems, and hardware groups, and shapes reference designs and long-term infrastructure