OmniML circular logo slowly moving on screen

About Us

OmniML is an artificial intelligence (AI) company that amplifies and enables powerful machine learning capabilities for users of all levels, with our software platform.


We pioneered this space and are passionate about perfecting it

See Open Positions


OmniML makes major ML tasks 10x Faster with 1/10th of the engineering effort.

OmniML builds machine learning (ML) development software to help our users design and train optimal models tailored to target hardware platforms which enable faster model speedups with higher accuracy and reduced engineering and deployment efforts.

Overhead view of vehicles at a street intersection

AI is already improving our lives in all imaginable areas, many of which require AI to run on edge devices for latency, cost, privacy, etc. However, in the AI industry nowadays, there still isn’t a good solution to design efficient models targeting AI capability on the increasingly diverse edge hardware. As a result, it takes repeated manual design and training iterations for model deployment, which in turn demands an extraordinary level of resource and engineering time for AI to reach production.

The team at OmniML is among a small cadre of AI/ML experts who know how to miniaturize deep learning models without sacrificing accuracy. As the publications from our research and at prestigious machine learning conferences, winning multiple awards along the way, our methods outperform peers in the market by a significant margin. OmniML is helping multiple customers achieve massive savings in computation and energy costs, our technology will enable powerful AI models deployed on all possible edge devices.

Woman wearing a virtual reality headset

Meet our Founders

Song Han

Co-Founder & Chief Scientist

  • Inventor of “Deep Compression”
  • Associate professor at MIT, PhD from Stanford
  • “35 Innovators Under 35” by MIT Technology Review
  • 33k Google Scholar citations


Co-Founder & CEO

  • Tech lead at Facebook AI, PyTorch accelerator enablement
  • Product and engineering leader at Falcon Computing Solution (acquired by Xilinx)
  • PhD from UCLA, years of experience in customized hardware systems at Intel Lab, MSRA


Co-Founder & CTO

  • Co-Inventor of “Deep Compression”
  • PhD from Stanford.
  • Worked at Google Research, Facebook AML and NVIDIA NVIDIA Fellowship Recipient

Awards/The Best Hardware Aware ML Platform

First place, the 6th AI Driving Olympics, NuScenesSegmentation Challenge @ICRA’21

First place, the 5th Low-Power Computer Vision Challenge, CPU detection track & FPGA track​ (Aug. 2020)

First place, 3D semantic segmentation challenge on SemanticKitti​

First place, the 4th Low-Power Computer Vision Challenge, CPU classification and detection track ​(Jan . 2020)

First place, the 3rd Low-Power Computer Vision Challenge, DSP track, @ICCV’19​

First place, MicroNet Challenge, NLP track (WikiText-103), @NeurIPS’19​

First place, Visual Wake Words Challenge, TF-lite track, @CVPR’19