>>> name = "Shyam Padia"

>>> university = "Northeastern University"

>>> languages = ["Python", "Java", "Node.js"]

>>> last_company = "Intuit"

 Education
  • Northeastern University
  • College of Computer and Information Science
  • Master of Science in Computer Science
  • December 2019
Programming Design Paradigms Information Retrieval Algorithms Natural Lanugage Processing Data Mining Techniques Special Topics in Artificial Intelligence Computer Systems Reinforcement Learning
  • University of Mumbai
  • Fr. Conceicao Rodrigues College of Engineering
  • Bachelor of Engineering in Computer Engineering
  • May 2016
Data Structures Artificial Intelligence Machine Learning Web Technologies Software Engineering Operating Systems Object Oriented Programming Cryptography Distributed Systems
Experience

  • Intuit

  • Software Engineering Intern (May '19 - Aug '19)

  • Software Engineering Coop (May '18 - Dec '18)

  • San Diego, California

Introduced faster OCR W2 PDF Upload in Income topic in the form of an AB Test resulting in 20% reduced tax prep time
Integrated Decision Engine for intent classification, replacing third party solutions and decreasing latency by 30%
Built a Case Deduplication Service with AWS Lambdas improving response times by 45% while mitigating 7% of duplicate cases
Created Smart Fields with React and PHP streamlining content publishing to prod by 30 mins and reducing 10% of case creations
Constructed a highly scalable General Redirect Service with AWS Lambdas and DynamoDB with 35% more efficiency

  • Outreach Circle

  • Software Developer (Nov '16 - May '17)

  • Bangalore, India

Developed a flagship feature for building distributed campaign organizers with Meteor.js and Angular, boosting canvassing efficiency and voter turnouts by 15%
Integrated contact matching with ElasticSearch between voter files and social media contacts increasing effective outreach by 10%
Designed highly customizable email templates for sending notifications to and from supporters using SendGrid
Generated campaign statistics in Chart.js to track supporter growth, outreach and identify super influencers

  • IIT Bombay

  • Research Intern (Aug '16 - Nov '16)

  • Mumbai, India

Created a micro service for automated recurring deliveries and invoice generation in Spring Boot and MySQL
Configured Nginx load balancer and API Gateway with Redis to improve reliability and enable faster transactions
Trained a Collaborative Filtering recommendation system for giving product suggestions with 87% precision

 Skills
Languages
Python
Java
JavaScript
C/C++
Scala
Lisp
SQL
PHP
VimScript
Tools
Pytorch
NLTK
Tensorflow
Matplotlib
Numpy
SKLearn
Pandas
OpenCV
OpenAI Gym
Frameworks
Angular
Express.js
Spring Boot
React
Meteor
Elasticsearch
Django
Databases
MySQL
DynamoDB
MongoDB
Oracle
PostgreSQL
Redis
Cloud
AWS
GCP
Platforms
Linux
MacOS
Windows
Android
Projects
Transferable Reinforcement Learning
Analyzed the potential scope of Transfer Learning in the Hand Manipulate Block and Egg environment from Open AI Gym with Q Learning, DQN and Policy Gradient Methods
Music Multi Transformer
Built four Music Transformers for each track inspired by Google Magenta and applied Global Multi Headed Attention allowing all decoders to attend over all encoders from all Transformers modifying the traditional architecture of a Transformer Network
Automatic Hypernym Detection
Trained several Matrix Factorization models on the Gutenberg corpus to automatically extract hypernyms from patterns
Fan Forge
Led a backend team of 5 and designed an open-source application where fans can curate ideas about exhibits and artifacts to be held in Comic-Con Museum using Express.js and AWS Lambdas
Text Reconstruction
Analyzed several models in Tensorflow for generating paragraph representations using VAE and Unidirectional LSTM Seq2Seq with/without Attention on Feature rich word embeddings retrieved from the Gutenberg Corpus
Deep Car
Assembled a self-driving RC car on a Raspberry pi, PWM driver with camera and trained on a CNN model in Keras based on data collected by driving on race tracks, performing on 96% accuracy
Search Engine
Implemented a multiprocessing Search Engine, Snippet Generator and Web Crawler with a MAP greater than Lucene combining several retrieval models such as BM25, Smoothed Query Likelihood and TF-IDF
SoNIC
Developed a social awareness network using Android, PHP and MySQL that aims to resolve common issues in the city of Mumbai by reporting them through proper channels
Nand2Tietris
Built a virtual computer based on an Operating System written in a custom programming language that runs on a simulated CPU architecture with an Assembler, Virtual Machine and Compiler in Python
Achievements
Innovator Award Comic-Con Museum/Intuit, Codechella 2018
Runner Up Paper Presentation, Technomania 2016
3rd Place
RIP The Crypt (TCS), Crescendo 2015