Hi! Welcome to my webpage. I am an independent researcher in AI safety and governance. I am a member at Trajectory labs, Toronto.
I am deeply interested in and dedicated to understanding how AI works. I see that as a pathway to design safer AI and to convincingly demonstrate when we should stop pushing the development of AI.
- Currently, I am working on a collaborated report on existential risks from AI commissioned by Institute for Technology Assessment and Systems Analysis at Karlsruhe Institute of Technology.
- From July-October 2025, I will be working from London Initiative for Safe AI (LISA), London, UK as a research fellow at LASR labs.
Previously, I was a Postdoctoral Scientist at Memorial University of Newfoundland, St. John’s working with Dr. Alex Bihlo in the broad area of machine learning.
You can find a list of my research work published in peer-reviewed Journals Here
Some of the things I am interested in:
- Understanding AI algorithms from the perspective of AI safety
- Alignment problem in Large language models
- Physics Informed Neural networks
- Geometric Group Theory
- Linguistics
- Education
- Research Mentorship
I currently live in Toronto, Canada and I love dancing, biking, yoga, hiking, and reading.
Previously, I have lived in
- Montreal, Canada
- St. John’s, Canada
- Mohali, India
- Gurgaon, India
- Delhi, India
- Rohtak, India
Contact Shivam Arora, Trajectory Labs 30 Adelaide St. East 12th Floor Toronto, ON M5C 3G8 E-mail: shivamaroramath at gmail dot com
