Résumé
Download PDF ↓Experience
Software Engineer (L4) · Google
- TL, Capping AdBrain Model Predictions: improved the capping framework to constrain over-prediction using Prediction Interval in a Poisson Log Loss DNN predicting pCVR, bringing Revenue Wt. Bias from +11 to -3.
- Lead, Attributed Branded Search (ABS) Modeling: leading ML strategy and measurement within the Glitter project to recover conversion losses from signed-out traffic.
- Project Lead, View-Through Conversion (VTC) Modeling: engineered and launched an end-to-end ML system to recover privacy-impacted VTCs for YouTube Demand Gen ads.
- Led a team (including an L3 engineer) to build a TFX-based pCVR model with iterative calibration.
- Optimized a high-throughput Flume pipeline processing ~20 billion daily ad impressions for YouTube's bidding systems.
- Promoted to L4 in 2024 with an "Outstanding Impact" rating; served as a C++ Readability Mentor, mentored 5 Nooglers, hosted 2 STEP interns, and conducted ~40 technical interviews.
AR/VR Intern · GMetri
- Built a toolkit to generate dynamic metaverses from user input using OpenAI's GPT model.
- Designed a UI for creating AI Brains and personalizing metaverses.
- Integrated APIs to connect components across the product.
SDE Intern · Cypherock
- Integrated new protocol and server APIs for cryptocurrency exchange.
- Built swap functionality for Bitcoin, Ethereum, Polygon, Solana, and ERC20 tokens in device firmware.
- Designed swap-flow screens for the desktop application.
Software Engineer Intern · Google
- Designed and built an email-based notification system for the Ads Resource Engineering team, from design doc to implementation.
- Implemented features, fixed bugs, and wrote unit tests for an internal Ads Planning tool (Java, Angular JS).
Student Intern · Summer of Bitcoin
- Improved User Statically Defined Tracing (USDT) support in Bitcoin Core by adding new tracepoints and eBPF-based scripts.
- Gave a talk on "Bitcoin Script" to an audience of 150.
Education
Indian Institute of Engineering Science and Technology, Shibpur · B.Tech, Computer Science and Technology (CGPA 9.62)
Skills
Languages — C/C++, Python3, JavaScript, Golang, Java, TypeScript
Frameworks — React, Vue3, Tailwind, Flask, Ruby on Rails, Express.js
Others — Firebase, MongoDB, PostgreSQL, Linux, Docker, Git
Publications
Detection of Cipher Types Using Machine Learning Techniques · Computational Intelligence in Pattern Recognition
- A sequence-to-sequence framework using CNNs and Transformers to automate classical cryptosystem identification, achieving 96.72% accuracy on a 130k ciphertext dataset.
Awards
Cyber-Security Hackathon, RISE
- 2nd position among 22k participants
Codevita 2022, TCS
- Ranked 98 globally among 136,054 students
Hashcode 2022, Google
- All India Rank 25, global rank 311
ICPC Asia Kanpur-Mathura Regionalist, ACM-ICPC
- Ranked 72 among 200+ teams
Summer of Bitcoin
- Selected among 50 students out of 5000+ applicants
Best Hardware Hack, Major League Hacking
- Won the 48-hour hackathon hardware category