Analyze, Test and Deploy AI from Anywhere, Anytime

Using the toolkit’s Deep Learning (DL) Workbench tool, developers can analyze and optimize their models—and now they can also remotely deploy on Intel® architecture using Intel® DevCloud for the Edge—an open development sandbox in the cloud.

With the integration, developers can compare, visualize, and fine-tune their models against multiple hardware configurations without the need for an Intel® processor on their bench.

Join Intel experts Marat Fatekhov, Jason Domer, Ramakrishna Dorairaju, and Zoe Cayetano to learn more about this new integration:

  • An overview of the new integration with Intel DevCloud for the Edge
  • How to use DL Workbench, the UI optimization tool in the Intel Distribution of OpenVINO toolkit, to easily visualize and analyze DL workloads.
  • How you can develop, fine-tune and remotely experiment using both the DL Workbench and the Intel DevCloud for the Edge



Ramakrishna Dorairaju, Lead Software Architect, Intel Corporation

Rama is a System Engineer focused on solving problems related to Edge Computing by bringing easy access to accelerated AI. Rama has 20+ years of experience in Embedded systems, Satellite broadcast & mobile communications and IoT/Edge computing domains, with a strong understanding of computer vision, cloud architectures and ML/DL Workloads.

Ryan Palmer, Developer Experience Architect, Intel Corporation

Ryan works within Intel’s Internet of Things Group to research and design optimal experiences for AI developers. He holds a M.S. in Human-Factors Engineering and has spent 15 years at Intel on the leading edge of innovation and design of hardware and software solutions.

Marat Fatekhov, Software Developer, Intel Corporation

Marat has more than 5 years of programming experience with focus on extending Intel portfolio of tools for Mobile, Media and AI markets. Currently working in the OpenVINO Deep Learning Workbench team. Marat holds Bachelor’s degree in Business Informatics and Applied Mathematics and Masters degree in Management from Higher School of Economics, Nizhniy Novgorod.

Performance varies by use, configuration, and other factors. Learn more at