At Periodic Labs, we are reimagining how scientific discovery happens through a culture of ownership and cross-disciplinary collaboration. Our team of physicists, chemists, and ML researchers identify and solve problems without boundaries or bureaucracy. We run weekly teaching sessions where physicists teach LLMs to reason about quantum mechanics while ML researchers learn physics fundamentals. We eagerly learn new tools and science to push forward our mission, believing that real breakthroughs require closing the loop between hypothesis and physical reality.
We are building AI scientists and the autonomous laboratories for them to operate in the physical sciences. Our approach recognizes that frontier AI models need more than internet text - they need real-world experimental feedback. Our autonomous labs generate gigabytes of experimental data that exists nowhere else, providing the reinforcement learning environment where nature itself becomes the teacher. From helping semiconductor manufacturers solve heat dissipation problems to discovering new superconductors, we optimize for deep learning and real impact. Whether working with space, defense, or semiconductor customers, we combine frontier AI models with physical experimentation to accelerate scientific progress.