● Developed 3D a pulmonary lung nodule detection network with deep-convolutional neural networkswhich achieved the sensitivity of 0.9 and 0.3 False positive per scan, tested on 491 Indian CT scans.● Trained a 3D CNN to segment Lung and Lung Lobes with a 0.97 and 0.93 dice coefficientrespectively.● Ranked 13th in Kidney & Tumor Segmentation Challenge. (KiTS21)● Worked On normal/abnormal chest X-ray detection and a triaging project which improvedteleradiology reporting time by 35%.● Managed a team of 4-6 radiologists throughout different project phases.● Coded internal library for ease of training and functions regularly used in training phases.● Coordinated with data-engineer to design Azure storage structures to facilitate easier datamaintenance and access across different projects.● Tech stack used in projects - Pytorch, Keras, Sklearn, Numpy, Opencv, Wandb, Pytorch Lightning,BitBucket, ClickUp

● Worked on Invoice parser to identify and extract important information from different invoices.

● Reproduced the code for FaceNet paper in Tensorflow to train a face recognition network● Face Liveness detection with local binary patterns(91% Accuracy on NUAA spoofing Dataset)● Developed POC web app for existing machine and deep learning projects.● Tech stack used in projects - Tensorflow, Keras, Sklearn, Opencv, HTML, bootstrap, and Django

● Worked on Front-End Development of multiple websites