Sign in

Engineer Data

Urbana, Illinois, United States
March 18, 2019

Contact this candidate



***, *** * *********** ****** Mobile: 217-***-****

Champaign, Illinois 61820, USA email:, Skills:

Data Science: Python with NumPy, Pandas, Matplotlib, SQL

Machine Learning: TensorFlow, Keras, Scikit-learn, Regression, Classification, Clustering, DNN, CNN, RNN, NLP

Programming Languages: Python, MATLAB, C (Basic), JAVA (Basic)

Software: SolidWorks, CATIA-V5, AutoCAD, ANSYS, Fluent, Gambit, Abaqus and Microsoft Office

Strong communication skills- oral, written, and presentation Work Experience:

Graduate Student Researcher - Renewable Energy & Turbulent Environment Group Spring 2018 – Fall 2018 University of Illinois at Urbana-Champaign

Researched the free fall dynamics of objects moving in turbulent and non-turbulent environment using PIV and PTV techniques

Summer Research Intern, Indian Institute of Technology (IIT), Bombay June 2018 – July 2018

Carried out research on the experimental and computational analysis of the aerodynamic performance of bio-inspired corrugated aerofoils

Graduate Engineer Trainee (GET), OCL Iron and Steel Ltd September 2015- August 2016

Received training in various departments of a steel plant. Successfully handled assignments pertaining to inspection, plant maintenance and production of steel billets and sponge iron Projects:

Predicting customer churn:

In this project I created a deep neural network using Tensorflow to predict whether a customer will make a new purchase based on his past purchasing history and feedbacks. The motivation for this project was to identify customers for targeted marketing strategy.

Classify Yelp reviews:

In this NLP project I classified Yelp reviews into 1-star or 5-star categories based off the text content in the reviews. This project gave me insights into text analysis using scikit-learn and pipeline method to simply the analysis process. One interesting observation was the use of Tf-Idf actually made things worse whereas using the pipeline with just the CountVectorizer and Naive Bayes gave a precision of about 0.93. Using Random Forest Classifier with Tf-Idf gave about 0.87 precision.

Aerofoil noise predictions:

The aim of this project was to predict the value of scaled sound pressure level using Regression machine learning models and later use the model to predict noise for data obtained from the wind tunnel measurements at the University. I used Linear Regression model first and then the Decision Tree Regressor. Out of the two models, the later performed better in predicting the values of noise.


Deep Learning Specialization - Coursera

Machine Learning with TensorFlow on Google Cloud Platform Specialization - Coursera

Data Science, Micro Masters, UC San Diego, edX: enrolled

IBM Professional Data Science - Coursera

Data Science and Machine Learning Complete Bootcamp - Udemy

SQL - MySQL for Data Analytics and Business Intelligence - Udemy

A Hands-on Introduction to Engineering Simulations, edX, Cornell University Education:

University of Illinois at Urbana-Champaign (UIUC) KIIT University Master of Science in Aerospace Engineering Bachelor of Technology in Mechanical Engineering December, 2018 May, 2015

Relevant courses: Mathematical Methods, Finite Element Analysis, Mathematics (1,2,3), Computer Systems and Programming

Contact this candidate