Sathish Sampath

MS CS Georgia Tech · 4 Years Experience · sathishsampath@gatech.edu

Full Stack Developer with 4 years experience in web/standalone application development with information extraction, natural language processing, computer vision and machine learning, and an enthusiast to learn and explore new technologies.

MS Computer Science student in Georgia Institute of Technology, specializing in Machine Learning. Graduate Research Assistant in Computational Enterprise Science Lab at Georgia Tech.


Experience

Graduate Research Assistant

Info Vis Group, Georgia Institute of Technology

Areas of Research: Data Mining, Natural Language Processing, Data Visualization and Machine Learning

  • Researched and developed an Intelligent Ecosystem Analyser in Python to extract structured and unstructured enterprise data, analyze it, determine the industrial trends and visualize it using D3.js
  • Developed Python Web crawlers to extract API information and Mashup from different sources, analyze the relationship between different APIs and visualize the API Ecosystem
  • Designed and developed Data pipelines to extract Company data from SDC Files and create network files for different Visualization tools.
August 2018 - Present

System Engineer(Developer R & D)

Tata Consultancy Services Ltd

Areas of Work: Information Extraction, Natural Language Processing, Web Development, and Machine Learning.

  • Designed and developed an Information extraction engine in Python using Optical Character Recognition(Tesseract), Natural Language Processor(NLTK, SpaCy, and RegEx) and WebCrawler(Mechanize) to extract vital information from hundreds of structured/unstructured documents/websites in a few minutes.
  • Built a Ruby on Rails web application to collect, store and version control multiple documents using Git. Developed and integrated the Python-NLTK Natural Language Processor to analyze the relationship between paragraphs of different documents. Reduced the time taken to find the impacted paragraphs in hundreds of documents due to a change in one document, from Months to Minutes. Deployed the application in analyzing the impact of Financial Regulatory changes over Loan/Credit Card Policy documents by a leading Financial Institution.
  • Developed a Python-Flask Web application to monitor and analyze the energy consumption pattern of the commercial buildings. Developed and integrated Machine Learning models using Python(Scikit Learn), to predict the future energy consumption and comfort requirement of different floors/rooms, and optimize it. The application is currently deployed in few buildings(with more than 10,000 occupants) and it helped the Building Management to reduce the energy bill by 5-15%.
December 2014 - July 2018

Education

Georgia Institute of Technology

Master of Science
Computer Science

GPA: 3.86 / 4.00

College: College of Computing
Specialization: Machine Learning
Completed Courses

  1. Machine Learning(CS 7641) - Professor Charles Isbell and Professor Michael Littman.
  2. Computer Vision(CS 6476) - Professor James Hays.
  3. Machine Learning for Trading(CS 7646) - Professor Tucker Balch.
  4. Knowledge-Based Artificial Intelligence(CS 7637) - Professor Ashok Goel.
  5. Data and Visual Analytics(CSE 6242) - Professor Guy Lebanon and Professor David Joyner.
  6. Artificial Intelligence for Robotics(CS 8803) - Professor Sebastian Thrun.
  7. Special Problem- Analyze the 10K Fillings of Fortune 500 companies using NLP, understand the strategies(success/failure) and visualize the industrial ecosystem. Researched under the guidance of Professor Rahul Basole
August 2017 - May 2019

Anna University

Bachelor of Engineering
Electrical and Electronics Engineering

GPA: 7.9 / 10

August 2010 - April 2014

Skills

Highlights
Technical Skills
Languages Python, Ruby, R, C++, SQL, HTML5, CSS3, Javascript
ML Libraries Scikit Learn, PyTorch, TensorFlow
Database PostgreSQL, Oracle, MySQL
OS Ubuntu, Unix, Mac, Windows, DOS & RHEL
Technologies Tesseract, Imagemagick, Git, Docker, MATLAB, Tableau

Certifications

    Deep Learning with TensorFlow - IBM Cognitive Class
    June 2018
    Machine Learning - Coursera, Stanford
    December 2014
    Mining Massive Datasets - Coursera, Stanford
    December 2014
    Deep Learning - IBM Cognitive Class
    June 2017
    CS188.1 Artificial Intelligence - EDX, UC Berkeley
    May 2015
    LINK5.10x: Data, Analytics, and Learning - EDX, University of Texas Arlington
    Decmeber 2014
    Process Mining: Data science in Action - Coursera, TU Eindhoven
    January 2015
    CS1156x Learning From Data (introductory Machine Learning course) - EDX, CaltechX
    Decmeber 2014
    R Programming - Coursera, The Johns Hopkins University
    June 2015
    From GPS and Google Maps to Spatial Computing - Coursera, University of Minnesota
    November 2014