Zettascale
Energy efficient chips for AI
What they do
AI training and inference in data centers are constrained by high energy use, heat, and inefficient compute on existing GPUs/TPUs, driving up cost and limiting performance.
Zettascale builds reconfigurable, energy-efficient AI accelerator chips (XPUs) that optimize model dataflow for faster training/inference with lower power and cooling needs.
Data centers and enterprises running large-scale AI workloads, including cloud providers and AI infrastructure teams.
Founders
Co-founder & CEO of the Zettascale Computing Corp., autodidact since age 9, with a background in Computer Science & Computer (Architecture) Engineering (BSc + MSc, dropout), mathematics, and aerospace.
Co-founder & CTO of the Zettascale Computing Corp., with a background in generative modeling
Open roles 2
Company timeline
- Founded2024
- YC batchSummer 2024
- StatusActive
- Team size4 people
- LocationSan Francisco, CA, USA
Similar startups
