The architectures that power modern AI were designed for language, not for science. They were never built to understand DNA, interpret experiments, or learn the rules that govern living systems. Closing this gap represents one of the defining opportunities of our time.

Our team has pioneered advances across frontier AI, including the first models trained with one-million-token context windows, and now scaling toward one billion. We focus on innovations on systems and architecture, because building AI for science demands a fundamentally different foundation. As a first application of this technology engine, we are advancing AI for life, the most complex and consequential domain of all.

We are the AI team behind Evo and Evo 2, the generative genomics models used to create real gene-editing tools and the first whole genomes designed entirely by AI. That work demonstrated that AI can create biology, not just analyze it. We are now building multimodal models trained directly on the fabric of biology, enabling faster discovery, deeper understanding, and entirely new capabilities.

As we push the frontier of scientific superintelligence, we will build systems hand-in-hand to ensure global biological resilience: rapid detection, rapid response, and rapid countermeasures against emerging threats, both natural and synthetic. Our mission is ambitious: to reimagine what AI can do for science, and to build that future.

If our vision resonates: hiring@radicalnumerics.ai

MICHAEL POLI, STEFANO MASSAROLI,
ERIC NGUYEN & ARMIN W THOMAS.