Shubham Bagi Email: *******.****@*****.***
www.linkedin.com/in/shubhambagi Mobile : +1-217-***-****
Website : shubham12595.github.io/ Kaggle : kaggle.com/shubham1205 Education
Stony Brook University Stony Brook, New York
Master of Science in Computer Science;GPA:3.7 Aug. 2019 - Dec. 2020
Courses taken - Machine Learning, Data Science, Arti cial Intelligence, Big Data Analytics, Theory of Databases;
B.V.Bhoomaraddi College of Engineering Hubli, India Bachelor of Engineering in Electronics and Communication; GPA:4 (9.15/10.0) Aug. 2013 { July. 2017 Programming Skills
Programming Languages: Python, C, SQL, Javascript, Java, C++
Skills:Machine Learning, Data Analysis, Software Development, NLP, Big Data, Deep Learning, Statistics.
Libraries: Pandas, Numpy, SciKit-Learn, matplotlib, Keras/TensorFlow, Pytorch, Mlib, BeautifulSoup, NLTK, Scipy, Seaborn, Plotly.
Databases/BigData: Map-Reduce, Hadoop, Spark, DB2, MySQL, SQL Server, MongoDB, Hive
Others AWS, REST, HTML5, CSS, Unix Scripting, OpenCV, ETL,Tableau, Oracle, XML, JIRA, Con uence, Git, MS-O ce, Selenium, Splunk,Postman.
Experience
Remote Roo ng SouthLake,Texas
Machine Learning Engineer-Data Scientist Intern May 2020 - Aug 2020
Improved data mining processes using classi cation algorithm and time series analysis resulting in 17% increase in accuracy and 19% decrease in time needed to infer insights and to develop marketing strategies.
Implementation of Deep Learning model using Mask R-CNN, MS COCO, ResNet101 to remotely inspect and assess roof damage; identi ed the roof damage with an accuracy of 96.58%.
Stony Brook University Stony Brook, New York
Teaching Assistant Aug. 2019 - Dec 2019
Orchestrated the TA duties of 250 under-graduate students under Prof. Michael Tashbook.
Robert Bosch Engineering and Business Solutions Bangalore,India Associate Software Engineer Oct 2017 - June 2019
Supervised a team of 4 in Germany as Functional Safety Developer, to achieve 80% reduction in testing time by developing autonomous testing software for fault management of CAN Frames.
Executed responsibilities on various requirements like Tester Diagnostic Services, CAN frames, Cruise Control functionality, Driver Demand Requests. Remodelled the safety software for complex systems like Engine Control, Remote Parking Assistant, Handling Transmission and Vehicle Stability interventions; increased the throughput by an average of 20% and reduced customer complaints by 50%. Projects
Twitter Sentiment Analysis - Drafted a data pipeline which extracts 6000 real time tweets using Twitter Stream API. Used AWS Kinesis FireHose, S3 bucket and Amazon Elastic MapReduce(EMR) to stream, store and analyse the Tweet Data with the help of PySpark from S3. Achieved an accuracy of 83%.
Political Polarization and Marriage - Collaborated to analyse the 20 million census data of Florida and New York state in order to obtain insights on the impact of political party a liation of 5 million+ couples on their marriages and its correlation to the divorces using Pandas, Numpy and Sklearn libraries.
MapReduce Library - Designed a Hadoop-like MapReduce facility,with master and worker nodes to process vast amounts of data in parallel on large clusters with 100% fault-tolerance.
Image and Video Classi cation using CNN and RNN techniques - Classi ed Human actions in images and video using CNN and RNN techniques and Pytorch with an accuracy of 89.93%.
Recommended System - Engineered a Recommended System using Item-Item Collaborative ltering method and minhashing method(Similarity Method) using Apache Spark and HDFS to achieve an RMSE of 0.765.
Spatial Queries Analysis on Covid-19(DB2) - Explored the New York Health Information and US Census to nd closest healthcare facility with ER Room for NY Counties using DB2 Spatial Databases.