• Develop advanced Machine Learning methods to analyze slide pathology images.

• Build REST API for finding regions of interest in Whole Slide Images.

• Deployed API on Harvard Cluster to be called by labs and IoT devices.

• Motivated Self-Supervised Learning for detecting regions of interest in an unlabeled set of slide images.

• Extend the existing framework by implementing and testing Graph Neural Networks, Vision Transformers, and other state-of-the-art models using Pytorch.

• Developed in Python a web library for understanding energy needs with graph modeling.

• Contributed to an existing framework by adding key features when handling networks and geodata.

Implemented and researched the various techniques of data augmentation to improve results on a complex multi-class segmentation problem. In the Medical Machine Learning department, I motivated the use of GANs to produce new samples for cancer cell detection.