Abir Chakraborty
Principal Applied Scientist Manager at Microsoft
Redmond, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolAbir Chakraborty is a Principal Applied Scientist Manager at Microsoft with a decade of experience translating research-grade machine learning into production systems across fintech, customer service, and recommendation domains. He holds a Ph.D. in Aerospace Engineering from IISc and has applied hybrid physics-ML approaches to problems like remaining useful life and injury prediction early in his career. At Flipkart and [24]7 he led ML efforts for credit-risk, adoption propensity, and conversational AI, and his recent open-source contributions include improving SASRec recommendation model implementations and tests in the well-regarded recommenders repository. Known for blending rigorous experimentation with production rigor, he moves teams from prototypes to validated, test-covered models. Based in Redmond, he pairs deep academic training with pragmatic product focus, often surfacing subtle data signals (alternate-data credit insights, voice/IVR context) that others miss.
10 years of coding experience
19 years of employment as a software developer
Ph.D Aerospace Engineering, Ph.D Aerospace Engineering at Indian Institute of Science (IISc)Bachellor of Engineering Civil Engineering, Bachellor of Engineering Civil Engineering at IIEST, Shibpur
English
Github Skills (7)
jupyter-notebook10
machine-learning10
recommendation-system10
tensorflow10
python10
data-science9
testing7
Programming languages (2)
Github contributions (5)
recommenders-team/recommenders
Sep 2021 - Mar 2022
Best Practices on Recommendation Systems
Role in this project:
ML Engineer
ML EngineerContributions:32 reviews, 27 commits, 3 PRs in 5 months
Contributions summary:Abir primarily focused on updating and modifying SASRec model implementations within the repository. They made changes to the example notebooks, specifically `sasrec-tf2.ipynb` and `sasrec_amazon.ipynb`, which suggest model training and experimentation. Additionally, the user added unit tests for the SASRec model and its components, including the WarpSampler, indicating a focus on model development and validation. They also upgraded the tensorflow version in the setup.py.
recommendation-systemspythonjupyter-notebookoperationalizationmicrosoft
aeroabir/SASRec-TF2
Sep 2021 - Mar 2022
SASRec implemented in TF2
Contributions:5 commits, 9 pushes, 1 branch in 5 months
tf2
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.