Hi, I'm Advay. I enjoy reading, football, and interesting conversations.
I’m an undergraduate studying Computer Science at the National University of Singapore.
Prior to coming to Singapore, I spent 12 years of my life in Kolkata, India, where I attended The Heritage School.
I'm spent the summer at the Apple HQ working on Machine Learning Infrastructure for Siri. I built a search indexing system to efficiently query Siri's ontology, and was selected to present my project to the head of Siri (Apple VP).
I took a semester off from school to intern at Twitter again. I worked on Applied Machine Learning for the Twitter Home Timeline. I used Deep Neural Networks to build predictive models for user engagement on videos. I launched many iterations of experiments to evaluate the performance of the models on production traffic.
I explored the use of Bayesian Optimisation and Automatic Differentiation for tuning the hyperparameters of Machine Learning algorithms, as a part of NUS' Undergraduate Research Opportunities Program (UROP). I played around with PyTorch and learnt a lot about Statistics and Machine Learning.
I'm a part of the Coreteam(and former President) of NUS Hackers, a student group dedicated to spreading Hacker culture in NUS and Singapore. I've helped organise Singapore's largest student run hackathon, organised weekly technical talks with speakers from the Industry/Academia, conducted workshops in technical topics for 50-100 students, and started a mock technical interview initiative.
I spent the summer of 2017 at the Twitter HQ in San Francisco working on Twitter Lite as part of the Responsive Web Team. I worked in React, Redux, and ES6. I built Twitter Lite's Live Video experience, and worked on integrating the Chrome credentials management API. All my code was shipped, and used by over 6 million users daily.
I've been a TA for Data Structures and Algorithms (Fall 2018, Fall 2017, Spring 2017) and Programming Methodology (Fall 2016). My responsibilities have included conducting Discussion Groups, grading assignments, and holding consultation sessions for students.
I spent the summer of 2016 working as a Full Stack Web Developer at Xfers, a startup from the YCombinator Summer batch of 2015 looking to simplify the Payments process in Southeast Asia. I helped build an onboarding system used daily by customers and also built an internal analytics dashboard.
A Distributed Maze game that allows users from multiple machines to play against each other. This was built for a Distributed Systems class, and I implemented Sequential Consistency and Fault Tolerance as per the project requirements.
A Convolutional Neural Network for the group project of a class, for a subset of the Labelled Faces in the Wild dataset. We applied data augmentation, automated hyperparameter tuning, and explored the use of the Facenet architecture. I personally worked on automated hyperparameter tuning, and the base CNN architecture in Keras. You can view the code here.
An IOS App that allows you to customize musical tracks and augment them with musical effects. You can learn more about the app, and see the code here. This project was built in a group of 4 and won the Best Project Award at my University's Biannual Showcase. I personally worked on designing APIs and data models, as well as integrating cloud-backed syncing and sharing features.
A Java based Tetris playing AI for the group project of a class. We used a combination of Genetic algorithm and a Particle Swarm optimisation routine along with multithreading to build an agent that cleared over 2 million lines. You can view the code here.
A Web App that takes in the Twitter handles of two people, uses the Twitter API to fetch the tweets of the people, and uses a Markov Model to generate new tweets, which it then places side by side in the form of a verbal battle. You can try it out here and view the code here. This was built at a hackathon in a team of four. I worked on the backend and on developing the Markov Model.
Other school projects include a simple HTTP Server, a reliable File Transfer Protocol over UDP, a simple Shell, a simple encrypted File System, and simple Search Engines based on the Vector Space and Boolean Retrieval Models.
I enjoy playing Football and was on my High School team for 6 years. I've also represented my Faculty and Residential College in the Inter Faculty Games and Inter Collegiate Games. Apart from that, I've won a silver medal at a State Level athletics meet while in school, and also enjoy Tennis and Swimming.
I served as the School Captain(equivalent of Head Boy) while in High School. In University, I'm a peer mentor in the University Scholars' Program, and am responsible for guiding juniors through some of the problems they face in University.
I was a part of my High School Debate team, and have participated in a few competitions. I've also recently joined my University's Parliamentary Debate society.