Ivan Zhang

Deep Learning and Infrastructure

I spend a lot of my time designing large scale systems and building infrastructure automation tooling for deploying production Machine Learning services.

Previously, I built cool stuff with folks at Cortex Labs, the Pressly backend team, lead engineering at Ranomics.

The rest of my time I dedicate to publishing deep learning research with FOR.ai. While waiting for experiments to finish, I build tooling for workflow automation to help researchers focus on research. I talk about some of my work here.


  • Unsupervised Cipher Cracking Using Discrete GANs (ICLR Poster 2018)
    Aidan Gomez, Sicong Huang, Ivan Zhang, Bryan Li, Muhammad Osama, Lukasz Kaiser
  • Targeted Dropout (NIPS CDNNRIA Workshop Poster 2018)
    Aidan Gomez, Ivan Zhang, Kevin Swersky, Yarin Gal, Geoffrey Hinton
  • Press

  • UofT News: Cracking the code: This group of U of T computer science researchers are decoding ciphers with AI