Hi. I'm a 24-year-old Machine Learning Engineer working with NCICS, NOAA NCEI and I have a master's degree in Computer Science(Data Science Track) from NC State University. I've 3+ years of experience designing, implementing, and deploying large-scale generative AI solutions on AWS. Expert in building distributed training pipelines, fine-tuning LLMs, and optimizing ML models. Proven track record of collaborating with cross-functional teams and enterprise customers to deliver customized AI applications at scale.
My favorite languages for programming, data analysis, ML models, and Gen AI.
My favorite tools for version control, code editing, data science and econometric analysis.
The paper discusses the development of an ensemble approach for detecting hallucinations in abstractive text summarization. Hallucinations, which are inaccuracies or information not present in the source text, pose a challenge for generating accurate abstractive summaries. The paper focuses on unsupervised metrics and examines their correlations and effectiveness in detecting hallucinations. By combining these metrics into an ensemble, the study demonstrates that LLM-based methods are more effective at identifying hallucinations than other unsupervised metrics. I present an improved ensemble for LLM-based evaluations, surpassing the previous state-of-the-art to reach 0.91 Pearson Correlation.
View Details
This project involves aspects of Computer vision and Machine Learning designed to extract meaningful data using image processing and use that data to train a HOG/SVM classifier to generate a system to reduce the wait time for cars and pedestrians in high-traffic zones.
View Details
FindMyRoomie is a Web Application that provides a platform for NC State students to find roommates of their preference. This application draws inspiration from the original NC State Web state and utilizes Django, Javascript, React, Postgresql, and Python. I made this project for a software engineering course and hence followed all the best practices for software development. This showcases my ability to collaborate with teammates on Github, handle timelines, utilize a diverse tech stack and overall contribute to a conducive development environment.
View Details
I used this project as a makeshift gauge to study the digital architecture of the tech behind music. At its core, it is a classifier model that works with frequencies and amplitude to categorize sound clips to the closest genre. I've experimented a lot with this project by trying to create a recommender system that can take two artists and recommend music based on similar artists and the closest genres. At times I've used different Neural network configurations and different models like SVM and Random Forest to increase accuracy. If you are a music lover like me, this is the dream project.
View Details
During my time at Kion Technologies as a SDE I developed an Activity Monitoring System using Django, Celery, and RabbitMQ that tracks user engagement, and migrated the system to a PostgreSQL backend, enhancing query times by 1.8x for 40k users. By containerizing the Django service with Docker, I cut deployment times by 2 seconds when using storages like Redis and DynamoDB. Additionally, I redesigned the REST API for CRM notifications in React Native, doubling user reach.
View Details
The pandemic has given me time to explore my interests and learn more about the field of statistics, mathematics, and data science. With help from my university, I completed nearly 35+ courses in Machine Learning, Deep Learning, Data Science and Finance. You can view a list of certifications along with their credentials below
View Details