My Personal Details

I have a knack for experimenting with new technologies and each day I try to learn and explore the new advancements taking place in the tech industry and the world. I also enjoy trekking and exploring new places, so I guess part of my eagerness to explore and keep myself updated stems from there. Currently I am pursing my Master's in Computer Science at University of Massachusetts Amherst.

I have worked as a Software Engineer at Oracle, which helped me gain experience in cloud product development. And now through my education primarily specializing in Machine Learning/AI, I have realized the extensive applications and research opportunities that are available and could be made use of, to make our daily lives better.

NLP

I am interested in exploring the knowledge present in written text and apply it to solve further downstream tasks.

Machine Learning

I love how pure mathematical calculations can be used to learn model parameters to eventually help humans in their daily tasks.

Data Science

Generating insights from raw data provides stakeholders with a visual understanding of their data to make more efficient business decisions

Cloud Computing

With the advancement in processing power, cloud technology has funneled an easy path to obtain the resources and also deploy scalable application with minimum downtime.

Full-Stack Dev

Developed models and business logic can be transformed and made available in the form of interfaces to end users for easy access.

Python 85%

Java 80%

Javascript 70%

SQL 85%

Databases 85%

NLP - Pytorch 70%

Data Analytics 55%

My Work

Some of the interesting work I have done :)

Twitter Sentiment Analysis

A Tweet sentiment classifier predicting the sentiment of the user tweet using HuggingFace Transformers.

COVID-19 Cognizance

Measuring the impact of the virus in the states and counties to enrich the process of tracking and forecasting the spread of the virus, using Tableau.

Classifying Audience Response on Political Speech

A model that generates sentence-level classification of audience reaction to transcripts of speeches.