• Worked on requirements for displaying smart inhaler health metrics, IoT feedback through AI based mobile application• Performed data processing – data cleaning, feature extraction, handled imbalanced dataset to ensure quality of input • Created Common Table Expressions (CTE), joins, subqueries providing reporting solutions reducing query execution time by 30%• Formulated Principal Component Analysis (PCA) for dimensionality reduction of customer data improving model accuracy by 25%• Obtained correlation matrix to derive feature correlations - positive correlations, negative correlations between features• Built classification models using Logistic regression, SVM, Decision Tree, Random Forest to predict respiratory diseases • Used TensorFlow and PyTorch to develop deep neural networks to predict 5+ underlying diseases in a product user • Fine-tuned, cross validated and optimized the machine learning models to achieve 97.8% accuracy

• Teaching assistant for Python, Machine Learning, UNIX Utilities, Shell Scripting courses and mentored around 100 students• Supervised various student lead projects which employed machine learning algorithms like decision trees, Natural Language Processing (NLP), Supervised, Unsupervised Regression models, Neural Networks, Deep Learning, SVM, clustering• Participated in all phases of data mining – data collection, data cleaning, developing models, validation, and visualization to deliver data science projects.

• Performed data Extraction, Transforming and Loading (ETL) between different systems• Wrote numerous complex SQL queries utilizing window functions for analysis and optimized the query performance by 70%• Prepared Data pipelines to move data from source to destination scheduling by Airflow• Built Data pipeline using AWS services and Airflow dependencies between AWS S3, AWS Lambda, AWS Glue and Redshift• Migrated on-premise data to AWS cloud and achieved the company’s goal of quitting the existing datacenters that resulted in 40% reduced energy consumption on datacenters.• Designed database schema and dimensional data modeling, implemented, and maintained pipelines for performance and scalability of Customer Data• Created several Databricks spark jobs with pyspark to perform several table operations• Gained working knowledge on Google Cloud Platform(GCP) services like compute engine, cloud storage, cloud DataProc, Cloud Pub/Sub, Big Query • Worked with CI/CD tools such as Jenkins and version control tool Git• Collaborated closely with data scientists to understand their data processing requirements and helped with effective cloud solutions optimizing resource utilization leveraging AI/ML models on cloud• Implemented data cleaning and ensured data quality, consistency, integrity using Pandas, Numpy• Developed machine learning model to predict the churn rate of the customers• Explored and analyzed the customer specific features by using Matplotlib, seaborn in Python and dashboards in Tableau• Provided automated product recommendations to the customers which involved training a machine learning model based on aggregated customer purchasing data. • Published order data through Kinesis firehose into Amazon S3 data lake and spined up an Amazon Elastic MapReduce cluster to produce a recommendations model using Pyspark.

• Written scripts to identify End of Life software deployed which was the potential risk to the client software environment• Prepared dashboards and visualized data using ServiceNow, Tableau and Power BI to show KPI in client software environment