Ritwik Gupta

Data Scientist | University of Pittsburgh '17

My passion is combining healthcare and machine learning to provide unique insights into human conditions that will allow us to live in a healhier and safer world. I love to play tennis and read cereal boxes, shampoo bottles, and books.


Machine Learning Researcher - CMU SEI Emerging Technology Center
June 2017 - Present | Pittsburgh, PA
Software Engineer (Temp) - UPMC Enterprises
November 2016 - April 2017 | Pittsburgh, PA

Working on data coherency platforms and the IBM Watson AI XPrize. Worked on an R&D data visualization platform meant to provide high-fidelity, realtime ADT feed metrics across all hospitals in the UPMC Health System.

Data Science Intern - Apple (Applied Machine Learning)
May 2016 - August 2016 | Cupertino, CA

Applied Machine Learning team. Implementing clustering algorithms on a large dataset that requires deep feature selection and natural language processing.

Data Science Intern - Staples Innovation Labs/Staples SparX
May 2015 - August 2015 | San Francisco Bay Area

Creating recommender systems from scratch for the Staples.com website and emails in the United States and Canada. Staples is the world's 2nd largest e-commerce retailer. My recommender model was put into production in the Staples weekly emails, going to millions of customers and businesses across the US.

  • Algorithms written in Python and Scala, using Apache Spark and Hadoop for distributed computing.
  • Staples SparX

Front-End/Mobile Developer - University of Pittsburgh (Chemistry)
January 2015 - Present | Pittsburgh, PA

Built the Pitt Quantum Repository, an online database for molecular data and interactive visualization. PQR also features a REST API to easily GET molecular data and structure.

  • Website built to be fully HTML5/CSS3 compliant, using the Flask MVC for Python as the backend.
  • Pitt Quantum Repository

Data Science Intern - University of Pittsburgh (Biomedical Informatics)
June 2014 - September 2014 | Pittsburgh, PA

Worked with Dr. Xinghua Lu to develop novel machine learning algorithms to solve the problem of identifying driver and passenger mutations given a human genome.

Research Intern - University of Pittsburgh (Biomedical Informatics)
June 2013 - August 2013 | Pittsburgh, PA

Published a paper on the distribution and frequency of contiguous palindromic sequences in the human genome with specific focus in regards to Acute Myeloid Leukemia with Dr. Ganapathiraju.



Python, Java, Scala, Swift, MATLAB, C


Apache Spark, Hadoop, Hive, Cassandra, Mesos, YARN, OpenMP, OpenMPI, TensorFlow, CUDA, Flask, Android


Tennis, Photography, Cooking