About Us
Normal Computing builds purpose-built AI for silicon engineering and is developing a new class of computing hardware, using its software to design its own chips. Founded by former members of Google Brain and Google X who helped pioneer AI for the physical world, the company delivers its software and hardware with the largest semiconductor design and manufacturing institutions. Normal has raised more than $85M in funding led by Samsung Catalyst Fund, with participation from Micron Ventures, Celesta Capital, Galvanize, ArcTern Ventures, and Eric Schmidt's First Spark Ventures.
Normal EDA
Normal EDA is a purpose-built AI platform for silicon engineering, combining LLMs with formal logic to accelerate teams from spec to silicon. The platform applies auto-formalization to turn natural-language specs into structured, machine-actionable design intent, with formal consistency checks at every stage. Normal EDA builds an understanding of your team's goals by integrating with their specs and workflow, and uses that context to generate, verify, and optimize engineering artifacts, learning continuously from feedback. It spans DV/RTL automation today and extends into physical design and unconventional silicon workflows, scaling across the entire engineering org without replacing existing tools or processes.
Normal ASICs
In parallel, Normal is advancing its Carnot hardware program, using Normal EDA to develop its own silicon IP. Normal has successfully taped out CN101, the world's first thermodynamic computing chip, targeting multi-modal diffusion model inference. Where conventional GPUs expend energy suppressing the inherent randomness of physical systems, Normal's physics-based ASICs work with those dynamics to compute more efficiently, unlocking a fundamentally new architecture for AI workloads like image and video generation.
Our Team
Normal emerged from Google X's "AI for the Physical World" moonshot, attracting leaders and builders from Google Brain/X, Palantir, Meta, Graphcore, Apple, Broadcom, NVIDIA, and national laboratories, alongside exited founders, IMO medalists, Rhodes Scholars, and PhDs with deep experience across AI, physics, and formal methods. From offices in New York, San Francisco, London, and Copenhagen, the team forward-deploys into production workflows to build deep partnerships with the world's leading semiconductor companies.
