Swapnil Gupta
Machine Learning Engineer at Meta
New York, New York, United States
Summary
👤
Senior🎓
Top SchoolSwapnil Gupta is a Machine Learning Engineer with nine years of experience building and productionizing recommendation systems and ML workflows, currently improving ads ranking at Meta’s Monetization CoreML team. He holds an MS in Computer Science from NYU and has a strong applied ML background spanning deep learning for recommendation models, NLP and computer vision for document intelligence, and multi-GPU research implementations from his IIIT-H days. Swapnil combines research-led experimentation (A/B tests and offline metrics improvements at Facebook/Meta) with pragmatic engineering—shipping data pipelines, feature engineering, and production deployment practices. He’s also an active open-source contributor with full‑stack work on the well-known Public Lab plots2 Rails project, demonstrating comfort across front-end templating, back-end controllers and APIs. Notably, his work at EY cut tax form processing times by up to 90% through automated form parsers, reflecting a knack for turning core ML advances into measurable business impact.
9 years of coding experience
6 years of employment as a software developer
Master of Science - MS Computer Science, Master of Science - MS Computer Science at New York UniversityBachelor of Technology - BTech (Hons in Robotic Vision) Computer Science, Bachelor of Technology - BTech (Hons in Robotic Vision) Computer Science at International Institute of Information Technology Hyderabad (IIITH)High School Mathematics and Computer Science, High School Mathematics and Computer Science at Indian School Sohar
Github Skills (12)
html10
ruby-rails10
javascript10
rails10
ruby-on-rails10
erb10
collaboration9
wikipedia9
json-api8
css8
testing8
user-friendly7
Programming languages (6)
Github contributions (5)
publiclab/plots2
Nov 2016 - Jul 2018
a collaborative knowledge-exchange platform in Rails; we welcome first-time contributors! :balloon:
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:20 PRs, 166 comments in 1 year 8 months
Contributions summary:Swapnil contributed to various aspects of the publiclab/plots2 repository, primarily focusing on front-end and back-end modifications. They implemented admin tools in the login menu, addressed map-related errors, and added an alert for accepted answers, indicating back-end logic changes. Additionally, they introduced a JSON API for wiki pages and integrated functionality for browsing other activities, displaying a wide range of skills including front-end templating, back-end controller adjustments, and potentially database interactions.
ruby-on-railsballoonexchangefirst-timersknowledge
500swapnil/Keras_Efficientnet_SSD
Aug 2020 - May 2021
A pure Tensorflow+Keras TPU trainable implementation of SSD (Single Shot MultiBox Detector) using different backbones of EfficientNet which can be replaced with any ImageNet backbone. Tested on the PASCAL_VOC dataset. Implemented several low level data preprocessing and augmentations in pure tf functions for faster computation.
Contributions:4 releases, 2 reviews, 17 commits in 9 months
data-preprocessingtpukeras-tensorflowtensorflowpreprocessing
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.