Ishwarya Sivakumar
Machine Learning Engineer at Meta
Atlanta, Georgia, United States
Summary
🤩
Rockstar🎓
Top SchoolIshwarya Sivakumar is a Machine Learning Engineer with eight years of experience building scalable ML systems at the intersection of NLP and graph-based methods, currently on the Facebook Profile Relevance team at Meta. She holds an MS in Computer Science (ML specialization) from Georgia Tech and has delivered production-ready forecasting and representation-learning solutions at Walmart that cut forecasting error and feature engineering runtime dramatically. Her work spans demand forecasting with transformers, embedding-driven cold-start strategies, and trust-and-safety RAG/LLM systems for harmful-content detection. An active contributor to the EVA DB project, she enhanced an ASL action-recognition pipeline and produced tutorial notebooks that bridge video analytics and database-backed AI apps. Comfortable across PyTorch, PySpark, BigQuery and retrieval systems like ChromaDB/FAISS, she combines research rigor from CLAWS lab experiments on temporal data drift with hands-on delivery in large-scale engineering environments.
8 years of coding experience
4 years of employment as a software developer
Higher Secondary, Higher Secondary at AV Meiyappan Matriculation Higher Secondary SchoolMaster of Science - MS Computer Science, Master of Science - MS Computer Science at Georgia Institute of TechnologyBachelor's degree Computer Science, Bachelor's degree Computer Science at College of Engineering, Guindy
English, German, Tamil
Github Skills (6)
computer-vision10
pytorch10
machine-learning10
deep-learning10
python10
user-manual9
Programming languages (5)
Github contributions (5)
georgia-tech-db/evadb
Sep 2022 - Jan 2023
Database system for AI-powered apps
Role in this project:
ML Engineer
ML EngineerContributions:43 reviews, 37 commits, 22 PRs in 4 months
Contributions summary:Ishwarya's contributions primarily revolve around enhancing and testing an ASL (American Sign Language) action recognition system within the EVA DB project. They updated the ASL UDF (User Defined Function) implementation, including bug fixes and incorporating a mapping file for action labels. Furthermore, they added a tutorial notebook to demonstrate the usage of the ASL action recognition functionality. The user's work involved video loading, analysis and visualization.
image-classificationvideogpt-4evaexploratory-video-analytics
IshSiva/eva
Sep 2022 - Sep 2023
Exploratory Video Analytics System
Contributions:8 pushes, 1 branch in 1 year
video-analyticsanalyticsexploratorymachine-learningvideo
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.