Data Engineer

Omkar Reddy Gojala

Æ 832-***-**** • Q ******.*@************.*** • omkar-reddy • Omkar20895

Boston, MA 02120 Availability: May 2021

Experienced and dedicated graduate student with 2+ years experience in agile software engineering and data science. Seeking opportunities to leverage statistical modeling and visualization in solving key business problems with data-driven decisions. Work Experience

ML Research Co-op Center for Complex Network Research, Boston, MA Sept 2020 - Dec 2020

+ Built a network percolation game, BLUE, using Open AI Gym to study attack/defense effects on 2-dimensional networks

+ Synthetically generated data using Monte Carlo tree search to identify varied quality game branches for training an agent

+ Implemented a policy-gradient learning network and deep Double Q-Learning agent to predict next best move

+ Bench-marked the number of moves taken to win with heuristic-based bots and achieved an 80% decrease in moves Research Assistant Center for Complex Network Research, Boston, MA June 2019 - Aug 2020

+ Collected and analyzed live power outage data across US and built an ETL pipeline using PostgreSQL to store the data

+ Developed time-series forecasting model to predict outages per day aiding utilities in better resource planning for restoration

+ Built a web-app using Flask REST API and displayed data on leaflet outage map serving as an outage data repository Software Engineer Juniper Networks, Bangalore, India July 2017 - Dec 2018

+ Built a customer ticket recommendation engine to identify semantically similar tickets, using Word2vec and KNNs, increasing the productivity of engineers by 50% and received “Juniper Spotlight: Best Performer of the Quarter” award

+ Engineered an inheritance-based template engine to help test engineers reduce redundancy and improve code reusability

+ Developed Tableau dashboards identifying KPIs to assist executives in tracking key deliverables and employee performance Software Engineer Intern III Juniper Networks, Bangalore, India Jan 2017 - June 2017

+ Developed a python based Automation Test Framework(ATF) to replace traditional framework used to test Juniper devices

+ Took ownership and implemented a multiprocessing paradigm in ATF reducing the run-time and man-hours by 40% Google Summer of Code Fellow The Apache Software Foundation May 2016 - Aug 2016

+ Collaborated with Data Scientists at NASA and developed a python utility library, podaacpy, to access data from NASA PO.DAAC, the library has been accepted by NASA Open Source repository and currently has 120,000 downloads Projects

Flickr Image Caption Generation Employed transfer learning with InceptionV3 and VGG16 models, and built an encoder- decoder architecture using LSTM for generating image captions on Flickr8k dataset. Deployed the app using Flask on AWS EC2. [Python, Keras, Deep Learning]

Car Insurance Fraud Detection Performed feature engineering and mitigated class imbalance using SMOTE. Predicted fraudulent transactions using various classifiers and achieved best precision of 96% using XGBoost [Python, Scikit-Learn] Yelp Reviews analysis using Latent Dirichlet Allocation Calculated the aspect-based rating for reviews using Latent Dirichlet Allocation by employing guided seed words significantly improving accuracy and convergence time [Python, NLP] Skills

Languages Python, R, Java, SQL, HTML, CSS

Tools & Technologies Flask, AWS, Tableau, PostgreSQL, GCP, Docker Jupyter, RStudio, Vim Libraries Scikit-Learn, NLTK, Tidyverse, NumPy, Pandas, Ggplot2, Matplotlib, Keras, TensorFlow Statistical Tools Machine Learning, Deep Learning, Hypothesis Testing, A/B Testing, Clustering, Data Mining Education

Northeastern University Boston, MA

Master of Science in Data Science CGPA : 3.8/4.0 Jan 2019 - May 2021 Courses: Algorithms, Probability and Statistics, Data Mining, Supervised & Unsupervised Machine Learning, Deep Learning Dhirubhai Ambani Institute of Information and Communication Technology Gandhinagar, India Bachelor of Technology in Information and Communication Technology July 2013 - May 2017 Achievements

+ Committer and Project Management Committee member at Apache Nutch and Apache Open Climate Workbench

+ Recipient of Google Summer of Code fellowship 2017 and 2016 on behalf of The Apache Software Foundation

+ Recipient of travel grant for ApacheCon:Big Data North America 2016 and presented on “Big Data in Biology”

Contact this candidate