Pure Photonic Computing
The Revolution of Information Technology

Play video to learn more

Our Vision
CogniFiber’s unique photonic technology is currently the only enabler of life-saving applications in verticals like Smart-Cities, Smart Mobility and Industrial IoT. These applications require real-time, high-performance, low-power, Edge-Computing systems which continuously optimize via on-site training. Scalable photonic computing, will not only relieve AI energy and deployment issues, but will make AI sustainable and accessible.
Our Mission
Becoming a world leader in the field of ML and AI infrastructure, offering unmatched value for our customer’s growth, by combing superior performance while saving energy and cost. CogniFiber targets multi-billion-dollar opportunities with solutions capable of 1,000x improvements.
DeepLightTM: Pure-photonic Super Computing
What makes DeepLight so powerful?

Combining unique photonic processors and brain-inspired architecture, pure-photonic computing systems can harness the immense speeds of optical communication and directly compute while data is streaming through fibers and glass Chiplets. Computing with photons from start to end, avoiding any photons-to-electrons conversion as well as any system bottlenecks, CogniFiber Deep Light Architecture can outperform the most advanced solutions over 1000X in every way.

DeepLight IP and Architecture were reviewed and endorsed by industry leaders from companies such as Intel, Seagate, AMD-Xilinx and others.

* DeepLight processors are expected 2023-2024

Current Status

Following previous PoCs and two investment rounds, CogniFiber has recently completed its Aurora system, the first world-wide pure-photonic system demonstrator.

Aurora reaches a staggering 100 million machine learning inferences each second, while consuming 270 Watt only, less than a single silicon chip.

While Aurora will be showcased with CogniFiber’s design partners, and is targeting small machine learning models, the company has already made significant progress toward the production of its first DeepLight processors, the core technology of CogniFiber’s future products which targets any model size.

The Roadmap
2023
DeepLight Processor 1.0 Manufactured
Aurora Partnership Program and Deployments
2024
DeepLight Processor 2.0 Manufactured
DeepLight MVP System Assembly + Client LOI
DeepLight Processor Licensing Customer
2025 Datacenter DeepLight Cabinet Sale/Lease
fiber-switch
Pure-photonic computing
Pure-photonic computing

Here’s why:
While many are adding photons to the mix and creating photonic processors within hybrid systems, we are the only company that’s taking computation out of the integrated circuit and into a pure-photonic system that shatters all existing barriers.

Our Founders
Our team of Co-Founders bring plenty of experience, not only in the intellectual and scientific arena, but in the world of business as well. Together they can boast more than 30 years of start-up experience (software, hardware, product and business) in more than 14 companies, 5 of which were co-founded, over 40 years of research and more than 50 patents.
https://www.cognifiber.com/wp-content/uploads/2022/01/Dr-Eyal-Cohen-3.png
Founder, CEO
https://www.cognifiber.com/wp-content/uploads/2021/12/Prof-Zeev-Zalevsky.png
Founder, CTO

Inspired by the great promise involved in combining optical communication platforms with the revolution of deep learning networks, Eyal set out to explore and map a brand-new field of in-fiber photonic computing.  In early 2019, leveraging his broad technical experience in neuroscience (Weizmann Institute), HW design (Mellanox, Saifun), algorithms development (Oren, MS Tech) and photonic computing research (Technion, Bar Ilan University, Hebrew University), Eyal co-founded CogniFiber with world-class photonics expert Prof. Zeev Zalevsky, CogniFiber’s CTO. He recruited an elite group of engineers, implementing the theory from the whiteboards into the lab.  During its first two years, CogniFiber developed and registered significant IP enabling a POC that dramatically supersedes the most powerful current AI acceleration technologies in terms of performance and power consumption.  Eyal is truly energized and excited to lead CogniFiber’s journey into the next technological revolution.

Prof. Zalevsky is a Full-professor and Dean of the Faculty of Engineering at Bar Ilan University. His research expertise involves biomedical optics, super-resolution, and electro-optical devices. He has published more than 450 peer-reviewed papers, 10 books, 30 book chapters, and around 100 patents. For his work and great service to science, he received many national and international scientific prizes. He is also  a co-founder and technological leader in many successful start-up companies that originated from technologies commercialized from his lab. Together with Dr. Cohen in 2012, Prof. Zavlevsky began the promising research endeavor which explored the implementation of in-fiber neural networks, enabling de-facto light speed inference computing.

Additionally to our founders, CogniFiber relies on an extraordinary team of experts across a wide variety of fields. Optics, AI and advanced electronics are just the tip of the iceberg. Developing and creating DeepLight™ Technology is a multidisciplinary effort, that wouldn’t be possible without the great and diverse team at CogniFiber.

Our Team
https://www.cognifiber.com/wp-content/uploads/2021/12/Yohay-Hayat.png
VP R&D
https://www.cognifiber.com/wp-content/uploads/2021/12/Tomer-Yanir-1.png
AI Scientist
https://www.cognifiber.com/wp-content/uploads/2021/12/Aviad-Sorek-1.png
Acting CFO
https://www.cognifiber.com/wp-content/uploads/2021/12/Or-Arbel-Arenfrid.png
Electro-Optics Engineer
https://www.cognifiber.com/wp-content/uploads/2022/12/roy-daya.png
GTM Advisor
Career

Electro-optical engineer specializing in fibers

We are looking for an electro-optics R&D engineer that will be a part of the R&D team that designs, assembles, tests and analyzes photonic computing systems, parts and devices. The job requires in-depth knowledge and experience in fiber optics and photonics, preferably specific to CogniFiber technology.

  • BSc in electro-optics / electronics engineering or related field from a leading and recognized institution
  • MSc or 2yrs experience – must
  • Ph.D. – advantage
  • Hands-on experience and in-depth knowledge in the following:
    • Fiber optics: types, physics, materials, features, applications, manufacturing, modulation etc.
    • Developing electro-optical systems including fiber lasers and fiber-connected components: design, POs, fabrication (SOWs), assembly, integration, testing, and debug, preferably in startup companies.
  • Coding: MATLAB and Python – must
  • CAD-based photonic simulation SW experience: (e.g. Rsoft, Comsol) – advantage
  • A thesis related to fiber optics / photonic devices – advantage
  • Experience with >10G optical communication components – advantage
  • Familiarity with components and optical communication systems – advantage

Contact us for more information and send relevant CV to [email protected] .

 


FPGA and RT engineer

We are looking for an R&D FPGA and RT engineer that will be a part of the R&D team that designs photonic computing devices and systems. The job requires in-depth knowledge and experience in Xilinx-based FPGA preferably specific to CogniFiber technology .

  • BSc in Electronic Engineering from a leading and recognized institution
  • Hands-on experience and in-depth knowledge in the following:
  • Verilog/VHDL – must
  • HLS – Advantage
  • Real-Time Embedded C programming – must
  • Electrical schematics reading.
  • Working with Xilinx Ultrascale+ devices – advantage
  • Working with Xilinx high-speed Transceivers – must
  • Working with Xilinx Vitis – must
  • Hands-On lab work – must
  • Experience with 10G optical communication FPGA programming – advantage

Contact us for more information and send relevant CV to [email protected].

 

 

News

    HQ - Rosh HaAin, Israel