About

Aishwarya Wesanekar is a highly skilled Software Engineer with expertise in Reinforcement Learning and Image Processing. She is currently working at Meta, where she is part of the Reinforcement Learning and Data Synthesis Squads, Probability Org. Aishwarya is responsible for implementing and working on online reinforcement learning with Vanilla Policy Gradient and Proximal Policy Optimization models for chip design optimization. She also ideates reward shaping for optimization of chip placement and transitions the code for GPU optimization. Aishwarya leads the reinforcement learning reading group and presents reinforcement learning tutorials for knowledge sharing. She also proposes and conducts design document discussion and sprint retrospective sessions for the team. Before joining Meta, Aishwarya worked as a Graduate Research Assistant at the University of Pennsylvania, where she worked on Safe Reinforcement Learning for human-robot interaction with Dr. Osbert Bastani. She developed models using conservative distributional online RL to ensure safety in autonomous vehicles and benchmarked model-based, imitation learning models in collaboration with MIT. Aishwarya also worked as a Teaching Assistant for ESE 542 Statistics for Data Science under Dr. Victor Preciado at the University of Pennsylvania. She monitored and responded to student questions on Piazza and conducted office hours and recitations to help and support students in the course. Aishwarya has a Master of Science in Computer and Information Sciences from the University of Pennsylvania and a Bachelor's degree in Information Technology from the National Institute of Technology, Kurukshetra, Haryana. She also attended Delhi Public School, Indirapuram. Aishwarya's technical skills include Software Engineering, Reinforcement Learning, AI, Image Processing, ML, Research Scientist, and Data Scientist. She has 1.51 years of relevant experience and is passionate about solving real-life business problems using various methods that are scalable and efficient. Aishwarya is an RL enthusiast and likes to research how to use machine learning to improve the performance of applications.