Gautham Vasan
Member Of Technical Staff at University of Alberta
Edmonton, Alberta, United States
Summary
👤
Senior🎓
Top SchoolGautham Vasan is a research-focused machine learning engineer and PhD candidate at the University of Alberta with a decade of experience building lifelong learning systems for robotics. Currently a Member of Technical Staff at Zyphra, he develops architectures for long-context memory, continual learning, and long-term reasoning, grounded in extensive work on online reinforcement learning, imitation learning, and sim-to-real transfer. His industry experience spans research roles at Sanctuary AI and Kindred.ai where he translated RL/IL advances into real-world manipulation systems. A DAAD-supported visiting researcher in Freiburg, he has explored integrating noisy EEG-derived signals into assistive-robot skill learning—an uncommon bridge between neuroscience signals and robot learning. Based in Edmonton, he combines deep academic rigor with practical robot deployments to push toward machines that learn and adapt throughout their lifetimes.
10 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy - PhD, Statistical Machine Learning, Doctor of Philosophy - PhD, Statistical Machine Learning at University of AlbertaChinmaya VidyalayaBachelor of Technology (B.Tech.), Instrumentation and Control Engineering, Bachelor of Technology (B.Tech.), Instrumentation and Control Engineering at National Institute of Technology, Tiruchirappalli
English, Tamil, Hindi
Stackoverflow
51reputation
11kreached
0answers
1question
Github Skills (32)
robot10
ranking10
matlab9
sdk9
react9
science9
computer-science9
cpp8
arduino8
ros8
package8
java8
robotics8
labview8
csharp8
Programming languages (5)
Github contributions (5)
gauthamvasan/rl_algorithms
May 2021 - Feb 2022
Simple, easy-to-use implementations of Reinforcement Learning (RL) algorithms.
Contributions:24 commits, 2 PRs, 18 pushes in 9 months
implementationsreinforcement-learningdeep-reinforcement-learningrl-algorithmsreinforcement
gauthamvasan/rl_suite
Feb 2022 - Mar 2024
A simple, easy-to-use testbed for Reinforcement Learning.
Contributions:33 PRs, 127 pushes, 42 branches in 2 years 1 month
reinforcement-learningreinforcementdeep-reinforcement-learningtestbed
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.