Data Engineering

/

S HRUTI YERAVADEKAR

Brooklyn, NY 347-***-**** ******@***.*** LinkedIn: linkedin.com/in/shruti-yeravadekar / Github: github.com/shruti-y EDUCATION

Master of Science, Computer Engineering GPA: 3.333 May 2021 New York University, Tandon School of Engineering, Computer Science and Engineering Dept, NY Coursework: Machine Learning, Deep Learning, Cloud Computing, Big Data Bachelor of Engineering, Information Technology GPA: 7.37 May 2019 Savitribai Phule Pune University, Pune, India

Coursework: Object-oriented programming, Database Management Systems, Mathematics/Statistics, Data Structures & Algorithms PROJECTS

CSAW HackML NYU - Neural Network Backdoor Detection and Mitigation [ Link ] Dec 2020

● Designed a backdoor detector for neural networks with malicious triggers with techniques like Neural Cleanse, Pruning and Gangsweep using Generative Adversarial Networks (Keras, TensorFlow)

● Developed and executed a code that repairs the neural network by removing the backdoored inputs Self-playing “Snake” game using Deep Q-Learning [ Link ] Nov 2020

● Developed a reward-based environment and a snake agent from scratch and implemented basic Q-learning to teach the agent how to maximize the reward without receiving the terminal penalty (CV2, PIL, Numpy,Pandas)

● Implemented a Deep Q-Network with CNNs as a function approximator for better performance & achieved a high-score of 22 on a 10X10 grid(Cuda, Keras, Tensorflow)

Big Data Analysis of NYC 311 Service Requests & Prediction of Resolution Time [ Link ] Apr 2020

● Implemented an ETL pipeline and formulated and validated hypotheses with exploratory data analysis( Airflow )

● Built & compared accuracies of different Classifier models (Logistic Regression, Random Forest, Decision Tree) to predict complaint resolution time with avg 74% accuracy (Pyspark, SparkML)

● Created an interactive front-end that pulled the resolution time from the pickled model & performed A/B testing for a better user experience (Flask, REST API)

Vaccination Demand Forecasting based on Probability Prediction (Team Lead) Bachelor’s Thesis May 2019

● Extracted vital features that affect vaccination status using PCA & built a Logistic Regression model that predicted probability of vaccination with 92% accuracy (SQL, Python Scikit-Learn, Flask)

● Created a plug-in for the hospital’s web portal to track inventory by applying demand-forecasting logic on the model’s output ( Flask, HTML, CSS, Javascript)

● Designed intuitive data-driven dashboards ( Tableau ) to evaluate effect of socio-economic factors on vaccination rate EXPERIENCE

Data Science Intern, AnalytiQ, New York Jun 2020 - Aug 2020

● Developed an NLP architecture to extract and process therapy notes datasets from different data sources in KNIME

● Optimized and integrated code for the LDA algorithm to match notes to diagnosis through topic detection Graduate Assistant-Enrollment Analyst, Team Lead, NYU Tandon Online, New York Dec 2019 - Present

● Led a team of six by organizing scrum meetings and trainings, & managed the applicant database on Salesforce

● Established closed-loop analytics and generated ad-hoc reports to track and analyze KPIs to drive business growth Data Engineer Intern, Bitwise Solutions, Pune,India Jun 2017 - Jul 2017

● Designed a data pipeline to store & update data to data warehouse efficiently to ensure quicker data pull in an Agile software development production environment

● Managed performance of SQL deployments and optimized SQL queries in platforms like SQLite, MS-SSRS

● Formulated customized metrics for intuitive insight-driven reporting through Power BI and Tableau Data Analytics Intern, deAsra(Persistent Systems), Pune, India Jun 2015 - Jul 2015

● Collaborated with vendor teams to acquire, assess and analyze product data and statistics

● Created and designed web content for assisting small entrepreneurs with legal, finance and operational consulting TECHNICAL SKILLS

Programming Languages/OS: Python, SQL, C++, C, R, HTML, CSS, PHP, JavaScript, Java, Scala, Linux, Android Frameworks/Tools : Spark, AWS, Hadoop, Airflow, Kafka, Docker, Hive, Flask, Tableau, Power BI Database Technologies: Oracle SQL, MySQL, SparkSQL, MongoDB, SQLite, HBase, NoSQL, PostgreSQL, Mode Libraries : OpenCV, TensorFlow, Keras, PyTorch, PySpark, SparkML, MapReduce, Scikit-learn, D3.js PUBLICATIONS Vaccine Viability Detection and IoT based Inventory Management System, Pune [ Link ] Apr 2018

Contact this candidate