Data Scientist

SAI PAVAN KARTHEEK SUNKARA

Syracuse, NY ***** C: 315-***-**** *******.*****@*****.***

Tools

• Python, C++, R, SQL, MySQL, PostgreSQL, MongoDB, Amazon Web Services, AWS Glue, Kinesis, Redshift, Kafka, HBase, Hive, Tableau, Power BI, Databricks, Google Analytics, Excel, Access, Visio, Word, PowerPoint, Git, Confluence, and Jira. Skills

• Tensorflow, Pytorch, Keras, Apache Spark, Scala, EMR, Docker, SageMaker, Hadoop, AWS Lambda, MapReduce, Database design & Management, ETL, Machine Learning, Deep Learning, Statistical Analysis, Accounting Analytics, Artificial Intelligence, Computer Vision, NLP, Numerical Analysis.

• Certifications: AWS Solutions Architect, AWS Machine Learning Speciality, Tableau Desktop Specialist Work Experience

Data Scientist 05/2020 to 09/2020

Your Perfect Dose Inc. Liverpool, NY

• Designed and deployed 3 fully automated end-to-end MySQL databases and managed them on AWS.

• Managed and lead a Machine Learning team of 5. Implemented reliable, scalable and automated real time machine learning and ETL pipelines using Kinesis, AWS Glue, EMR, EC2, S3, CloudWatch and Lambda.

• Designed and deployed the architecture and solutions required by the web application fully on AWS for under 62 dollars per month, and completely eliminated on-premises infrastructure costs quoting thousands of dollars.

• Mined and analysed gigabytes of historical medical data and provided real time ML solutions for medical dosage recommendation using deep learning, unsupervised learning methodologies for text and numerical data.

• Deployed and managed networking and security solutions for the web-application on cloud and managed systems integration, network connections and configurations among servers and services.

• Worked with Product managers, App developers, and founders to pitch the product and secured 320,000$ investments from angels and partners.

Data Analyst 02/2017 to 12/2018

BSNL Telecom Services Pvt Ltd Hyderabad, India, Telangana

• Network Optimization [Languages/Tools: EC2, EMR, Spark, SQL, Git, Python, AWS Services, SageMaker]

• Developed real-time and predictive analytics solutions to analyse subscriber behaviour, avoid bottlenecks, predict data usage, peak load analysis and create individual network usage policies leading to identify trends, create forecasts, and mine data driven insights which effectively decreased Q/Q network infrastructure & maintenance costs by 38% and Y/Y by 17%.

• Churn prevention [Languages/Tools: Athena, EMR, FLUME, SQOOP, HDFS, Spark, RDS, Tableau, Python, Jupyter]

• Employed predictive analytics and real-time solutions on a data of around 70 Terabytes to successfully predict churn with an AUC of 89.9%, and 87% for XGBoost, and Random Forest. First of its kind approach based on Bayesian, Neural Networks, and SVM methodologies are implemented. The percentage of the retained customers was about 67% from all customers predicted to churn. This also increased the company revenue by 8% with 14-fold increase in churn prediction. The work also led to the re-profiling of the subscriptions and plans and provide better market segmentation.

• Developed a chatbot for the mobile application using AWS services to search FAQ using voice chat interface.

• Analyzed big data files of tens of gigabytes for business drive & insights and helped convey them using dashboards, stories, and presentations. Drafted and managed KPI reports to monitor service levels, identify trends, apply market research, and execute root cause analysis.

Education and Training

Master of Science: Applied Data Science Expected in 12/2020 Syracuse University Syracuse, NY

• Coursework in Analytical Data Mining, Data Analysis and Decision Making, Accounting Analytics, SQL Database Design, Administration and Management, Artificial Intelligence Principles & Algorithms, and Big Data Analytics. Bachelor of Science: Electronics & Communications Engineering 06/2018 Amrita University Bangalore, India

• Minor in Information Theory and Coding Techniques, Computer programming, Business Communications, and Operations Research.

• Ranked in Top 10% of the class for the 2014 batch.

• Placed first in Engineering Mathematics-III (calculus & Matrix Algebra) among 600 others. Additional Experience & Accomplishments

• IEEE Research paper on a semi-automatic locomotive prototype that runs on rail tracks, monitoring its surface health by analyzing real- time image data (image processing) based on machine learning models and communicating with the nearby stations. This proposed to reduce the maintenance expenditure by 16000 INR for every 10km of track. https://ieeexplore.ieee.org/document/8554526

Contact this candidate