After a decade of hype, we’re cutting through the noise—because real progress in neuromorphic computing needs more than just buzzwords. Without co-developing accelerators and circuits, the entire field remains theoretical, and let’s be honest, the projected gains are often wildly inflated.
We’re changing that.
We build neuromorphic accelerators with a sharp focus on:
🔹 Next-gen platforms that push the boundaries of computing
🔹 Seamless integration with silicon electronics at the chip and board level
🔹 End-to-end implementation starting from materials and devices to AI and ML models
🔹 Accelerators optimized for both AI inference and training
This isn’t just about rethinking digital and analog computing—it’s about pioneering radical architectures like attractor-based computing and cellular neural networks.
Today we are building the world’s first molecular neuromorphic SoC. Specific details we work on, are:
🔹 Neuromorphic accelerator integration with Si platforms
🔹 Mixed-signal circuit design
🔹 Firmware development
🔹 Full-scale SoC development
🔹 Software stack optimization
We are looking for electrical and electronics engineers, computer scientists, and chip designers ready to redefine the future of computing. Let’s make it happen. 🚀
Reference
Sharma, D., Rath, S.P., Kundu, B.,Korkmaz, A., Thompson, D., Bhat, N., Goswami, S., Williams, R.S. and Goswami,S., Linear symmetric self-selecting 14-bit kinetic molecular memristors. Nature, 633,560–566 (2024). https://doi.org/10.1038/s41586-024-07902-2
Sreebrata Goswami, R. Stanley WillIiams and Sreetosh Goswami*,Potential and challenges of computing with molecular materials. Nature Materials(2024): 1-11. https://www.nature.com/articles/s41563-024-01820-4