Synthara develops ComputeRAM, a patent-pending approach that adds in-memory computing capabilities to conventional on-chip memories to accelerate and reduce energy use in embedded microcontrollers. ComputeRAM is designed to deliver roughly a 100x improvement in both latency and energy efficiency for AI-rich embedded applications such as robotics, sensing, and wearables. The company says the technology will lower costs and time to market for device makers and enable new classes of feature-rich products. Synthara plans to introduce ComputeRAM to embedded computing applications and work with an early adopter community to integrate the technology into autonomous robotics, real-time personalized wearables and smart sensor networks. Financially, the company has closed over USD 11 million in equity and grants to bring ComputeRAM to market. Synthara was founded in 2019 as a spin-off from the Institute of Neuroinformatics at ETH Zurich and the University of Zurich and has a team of 18 employees. Synthara is developing next-generation AI chips and bespoke chip designs optimized for intelligent sensors with highly dynamic compute workloads. The company's technology builds on interdisciplinary research in system architecture, neuroscience, and neural networks at the Institute for Neuroinformatics of the University of Zurich and ETH. Target applications include wearables, IoT, and monitoring, and an Early Adopter program has already drawn interest from several market leaders. The company expected first products in 2022. The Zug-based spin-off completed an oversubscribed seed financing with investors including High‑Tech Gründerfonds and Zürcher Kantonalbank. Founder and CEO Manu V. Nair said the company is aiming to capture a share of the fast-growing multi-billion-dollar AI-chip market and to create double-digit numbers of high-tech jobs in Switzerland and Germany.

Total raised

$11M

Funding rounds

3

Latest round

Equity

Latest activity

Jun 2024