About Me
Hello! I am an Applied Scientist at Amazon Personalization working on reinforcement learning (RL) and recommender systems. I completed my Ph.D. in Computer Science at Harvard University advised by Professor Finale Doshi-Velez and Professor Susan Murphy. My primary research focus is designing and deploying online reinforcement learning (RL) algorithms for real-world systems.
Even earlier, I was a Technical Lead: Software Engineer at Amazon Groceries (Wholefoods Market, Prime Now, & Amazon Fresh) and earned a B.A. in Applied Mathematics at UC Berkeley.
News
August 2025 - Our Non-Stationary Latent Auto-Regressive Bandits paper was accepted to RLC 2025.
June 2025 - I have started as an Applied Scientist at Amazon Personalization.
May 2025 - I graduated with my Ph.D. and defended my thesis on Deployable Online Reinforcement Learning Algorithms. My thesis committee members were Finale Doshi-Velez, Susan Murphy, and Himabindu Lakkaraju.
February 2025 - Our Oralytics deployment paper has been accepted and awarded a full-length presentation at IAAI-25 / AAAI-25. This paper conducts post-trial re-sampling analyses to evaluate the algorithm. Results indicate that the Oralytics algorithm did indeed learn the advantage of one action over the other in certain states.
November 2024 - I was invited to give a talk at SLDS 2024 in the ``Statistical learning in clinical trials” session. I presented our recent Oralytics deployment paper.
July 2024 - The Oralytics clinical trial has completed!
May 2024 - I presented our Monitoring fidelity paper at the Society for Clinical Trials Annual Meeting.
February 2022 - The patent on Item identification based on receipt image filed while I was a Software Developement Engineer at Amazon was issued!