Shantanu Agarwal
Software Engineer at Meta
San Francisco, California, United States
Summary
👤
Senior🎓
Top SchoolShantanu Agarwal is a software engineer with a decade of experience building ML-driven systems, currently working on agentic AI at Meta after a rapid progression through AI and security-focused roles at Balbix. He holds a Bachelor's in Mathematics & Computing from IIT Guwahati and is pursuing advanced CS study at UMass Amherst, blending strong theoretical foundations with production engineering. His background spans end-to-end ML work—from collecting and crowdsourcing dialog datasets at IIT Delhi to deploying NLP models for vulnerability mapping in cybersecurity—demonstrating both research chops and product delivery. Earlier quant and engineering roles at Goldman Sachs and Samsung sharpened his systems thinking and performance-oriented approach. Based in San Francisco, he moves comfortably between research, model engineering, and applied security work, often owning projects from data collection through deployment. A less obvious strength is his history of contributing practical low-level improvements (e.g., C++ interfaces for deep learning stacks) that accelerate team productivity and model performance.
10 years of coding experience
4 years of employment as a software developer
Bachelor's Degree Mathematics and Computing, Bachelor's Degree Mathematics and Computing at Indian Institute of Technology, GuwahatiMaster of Science - MS Computer Science, Master of Science - MS Computer Science at University of Massachusetts AmherstHigh School, High School at Maheshwari Public School
English, Hindi
Github Skills (24)
dialogs5
self-attention5
dialog5
feature-extraction5
evaluation5
recycling4
retrieval4
transfer-learning4
nlp4
deep-learning3
python3
jekyll-theme3
kaggle3
computer-vision3
pytorch3
Programming languages (3)
Github contributions (5)
ashantanu/kaggle_house_pricing
Oct 2018 - Jun 2020
Kaggle house pricing
Contributions:1 PR, 2 pushes, 1 branch in 1 year 7 months
kagglehousepythonmachine-learningpricing
dair-iitd/FloNet
Nov 2021 - May 2022
Code for "End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs"
Contributions:9 commits, 8 pushes, 1 branch in 6 months
flowchartend-to-enddialogsend-to-end-learning
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.