Kushal Arora

I am on job market looking for industry research positions.

Hello!! I am a final year Ph.D. student at McGill University and Mila. I am jointly supervised by Prof. Jackie Cheung and Prof. Doina Precup.

My research focuses at the intersection of language modeling and reinforcement learning with the aim of building language generation models that are do not degenerate, are safe, honest, and are aligned to human preferences and values.

During my Ph.D. I have interned at Borealis AI with Layla El-Asri, Microsoft Reserach with Oriana Riva, and Meta AI (FAIR) with Jason Weston.

Before joining McGill University, I was an engineer at Amazon Alexa’s Algorithms team. My work there focused on scaling distributed deep learning approaches for speech and language understanding.

Prior to that, I was a master student at University of Florida where I worked with Prof. Anand Rangarajan on compositional language modeling.

Research Interests: Natural Language Generation, Reinforcement Learning, Imitation Learning, AI Safety and Alignment, Toxicity and Bias in Language Generation, and Code Generation.