# EnCharge AI

> EnCharge AI is a Santa Clara semiconductor startup, spun out of Princeton University, building AI accelerator chips based on analog in-memory computing. Its charge-based architecture runs heavy AI workloads on laptops, workstations and edge devices at roughly 20x the energy efficiency of conventional GPUs. Its first product, the EN100 accelerator, delivers 200+ TOPS within an 8.25W power budget, aiming to move generative AI out of the data center and onto the devices people actually hold.

- **Founded:** 2022
- **Headquarters:** Santa Clara, California, United States
- **Founders:** Naveen Verma (Co-Founder & CEO (Princeton professor)), Kailash Gopalakrishnan (Co-Founder & CTO (ex-IBM)), Echere Iroaga (Co-Founder & COO (ex-Macom))
- **Team size:** ~90 employees
- **Products:** EN100 AI Accelerator, Analog in-memory computing IP
- **Notable:** Closed an oversubscribed $100M+ Series B in February 2025, bringing total funding past $144M., Announced the EN100, billed as the first AI accelerator built on precise, scalable analog in-memory computing., Delivered 200+ TOPS within an 8.25W power envelope on an M.2 module - roughly 20x more energy efficient than comparable GPUs.

## Products & services

- **EN100 AI Accelerator** — First-of-its-kind AI accelerator built on analog in-memory computing. Available as an M.2 module for laptops (200+ TOPS at an 8.25W power envelope) and a PCIe card for workstations (four NPUs reaching ~1 petaOPS). Targets on-device generative AI, computer vision and image generation.
- **Analog in-memory computing IP** — Charge-domain compute architecture that performs multiply-accumulate operations using precise metal capacitors, reading results from the electrical charge on memory planes rather than individual bit cells - delivering up to ~20x better energy efficiency than conventional digital accelerators.

## Achievements

- Closed an oversubscribed $100M+ Series B in February 2025, bringing total funding past $144M.
- Announced the EN100, billed as the first AI accelerator built on precise, scalable analog in-memory computing.
- Delivered 200+ TOPS within an 8.25W power envelope on an M.2 module - roughly 20x more energy efficient than comparable GPUs.
- Won an $18.6M DARPA award to advance in-memory AI computing.
- Spun more than eight years of Princeton research across multiple generations of silicon into a commercial product.

## Latest updates

- **2025-05** — Announced the EN100 AI accelerator in M.2 (laptop) and PCIe (workstation) form factors, with an early-access program.
- **2025-02** — Closed oversubscribed $100M+ Series B led by Tiger Global; total funding surpasses $144M.
- **2024-03** — Partnered with Princeton on a DARPA-funded in-memory AI chip project ($18.6M award).

## Links

- Website: https://www.enchargeai.com
- LinkedIn: https://www.linkedin.com/company/encharge-ai

---

Profile page: https://yespress.io/encharge-ai
Published by YesPress — https://yespress.io
Last updated: 2026-06-09