# Opticore

> Opticore is a photonic computing startup building optical processing units (OPUs) - chips that run AI workloads with light and waveguides instead of electrons. Spun out of research at MIT, USC and UC Berkeley, the company claims its photonic chips are up to 100x more energy efficient and offer roughly 25x the computing density of leading GPUs, using time-multiplexed computing to encode as many as a trillion parameters on a single chip. Opticore has raised about $14.5M to date to attack the energy and 'memory wall' bottlenecks of AI data centers.

- **Founded:** 2024
- **Headquarters:** Berkeley, California, United States
- **Founders:** Zaijun Chen (Co-Founder & CEO), Ryan Hamerly (Co-Founder), Mengjie Yu (Co-Founder)
- **Team size:** ~16 employees
- **Products:** Optical Processing Unit (OPU), Time-multiplexed photonic compute, Co-packaged optics + HBM integration
- **Notable:** Raised approximately $14.5M in total funding across seed and seed-extension rounds, Demonstrated ~100x energy efficiency and area density improvement, published in Nature Photonics (2023), Original theoretical proposal published in Physical Review X (2019)

## Products & services

- **Optical Processing Unit (OPU)** — A photonic computing chip that performs GPU-class AI computation using light and waveguides instead of electrical components, claimed to be up to 100x more energy efficient and ~25x denser than leading GPUs.
- **Time-multiplexed photonic compute** — A patented encoding approach that reuses optical hardware across time slices, enabling up to a trillion parameters to be encoded on a single chip at roughly 100 TOPS/W efficiency.
- **Co-packaged optics + HBM integration** — Integration of silicon photonics with optoelectronic packaging and high-bandwidth memory to address the electronic 'memory wall' for AI training and inference.

## Achievements

- Raised approximately $14.5M in total funding across seed and seed-extension rounds
- Demonstrated ~100x energy efficiency and area density improvement, published in Nature Photonics (2023)
- Original theoretical proposal published in Physical Review X (2019)
- Further validation published in Science Advances (2025)
- Recipient of DARPA NaPSAC award and an INSPIRED award
- Founder Zaijun Chen: 2023 Optica Foundation Challenge Award and 2023 SPIE AI/ML Award recipient

## Latest updates

- **2025-09** — Raised an additional $7.5M in funding, bringing total to ~$14.5M, co-led by Jetha Global and Origin Ventures.
- **2025-01** — Published further technology validation in Science Advances and received an INSPIRED award.
- **2024-12** — Announced launch and initial seed funding to develop optical GPUs for lower-energy AI computing.

## Links

- Website: https://opticore.ai
- LinkedIn: https://www.linkedin.com/company/opticore-inc
- Twitter/X: https://x.com/ZaijunC

---

Profile page: https://yespress.io/opticore
Published by YesPress — https://yespress.io
Last updated: 2026-07-03