Omid Vaheb

Hi there 👋 Thanks for stopping by!

I am an engineer with a passion for solving real-world problems—especially the ones that seem impossible at first. My journey started in Electrical and Computer Engineering, but I quickly got hooked on AI and never looked back. I love tackling tough problems, whether it’s making systems more efficient, enhancing images, or figuring out new agents released everyday!

Currently, I’m at REDspace, working on improving Automatic Speech Recognition (ASR) with a Multi-modal approach and LLM oversight. I also collaborate with the amazing folks at the Vector Institute. Over the past two years, I’ve been diving into Astronomical Imaging at the University of Toronto and National Research Council Canada, finding ways to improve raw telescope data using Image enhancement techniques. Before that, at the University of Tehran, I explored AI in healthcare, developing deep learning models for Detecting Autism from infants’ crying audio and using EEG signals to aid in epilepsy and Parkinson’s detection. Basically, if it involves AI, data, and making things better—count me in!

When I’m not buried in code, you’ll probably find me geeking out over 3D printing 🖨️, attempting a series marathon 📺, getting overly invested in soccer ⚽, or playing old strategy games 🏰!