3D render of a molecular ball-and-stick structure

Ab Initio Design at Scale

Ab initio materials design is one of the hardest problems in science because it sits at the intersection of theory, computation, and synthesis. Designing materials with stable atomic structure means navigating an enormous, high-dimensional search space with countless local minima — far too large for ab initio simulation alone to be cost-effective.

We use AI to accelerate ab initio materials design. By fusing physics-based modeling with AI-generated heuristics, and by keeping human experts in the loop, we reduce the search space from exascale to feasible.

Learn more about our approach

Synthesis Is Part of the Design

Designing a synthesis pathway involves complex thermodynamic and kinetic barriers that cannot yet be fully modeled, and the cost of physical synthesis and testing can be prohibitive, even with robotic equipment. So we embed synthesis directly in the design loop, turning theoretical predictions into tangible discoveries. Our diffusion models suggest synthesis pathways, which are then ranked by our AI-generated heuristics before a single experiment is run.

Human Expertise, AI Speed

Our goal is to scale ab initio design and synthesis by raising the level of abstraction — from first-principles calculation to AI-generated heuristics — without losing the judgment that comes from experienced materials scientists, physicists, and chemists. Every candidate structure and pathway our models propose is reviewed by our team before it reaches the lab.

We're hiring

We're looking for materials scientists, physicists, and chemists eager to shape the future of intelligent materials discovery.

Computational Chemist

DFT & Atomistic Simulation · Bengaluru · Full time

View role

Machine Learning Engineer

Atomistic Simulation · Bengaluru · Full time

View role