I am a Research Scientist at OpenAI. Before that I graduated with a Ph.D. from UMass Amherst, advised by Prof. Andrew McCallum. I am interested in multiple areas of research in machine learning and Natural Language Processing (NLP). The overarching goal of my research is to enable human-like generalization in machine learning models -- touching on data/compute efficiency, unsupervised learning signals, and incorporating external knowledge. Most recently, I have been interested in improving the generalization of NLP models with limited human-labeled data through meta-learning, self-supervised learning, and multi-task learning. In the past, I have developed machine learning methods for various applications in recommendation systems, information extraction, knowledge representation, and reasoning. I have also dabbled in reinforcement learning for multi-agent systems to train agents that show complex emergent behavior without explicit human-designed rewards and learn to continuously adapt to changes in their environment. I have been fortunate to have interned at Facebook, OpenAI, Google Research, and Microsoft Research.