Developing a HIPAA-compliant Voice AI Agent tailored for healthcare applications, integrating advanced speech recognition and natural language understanding to facilitate secure, real-time patient-provider interactions, thereby enhancing patient engagement and streamlining clinical workflows

Assisting in the development of an AI platform that enables top healthcare companies to communicate with their patients more deeply and richly, resulting in tailored engagement and improved clinical results.

Organizing and hosting "Synthetic Image and Text Classification" hackathon, the first of its kind for Syracuse University, engaging over 100 students in innovative data science challenges, leveraging Kaggle.

Managing 5-person team responsible for development of machine learning models & creation of datasets for categorizing false content

Spearheaded the development of publisher & subscriber modules, seamlessly integrating 10 different data source APIs for real-time data ingestion & analysis, significantly enhanced conversion rates by 22% through improvements in the product showcase catalog.

Managed over 80 pull requests on GitHub, collaborating in agile team sprints, and developed 30 user stories using Jira tool.

Developed API key management for daily requests through JSON authentication in the PyEnsign development.

Authored & published PyEnsign Data Science articles, boosting customer understanding and engagement, thus elevating brand visibility.

Actively participated in building data platforms for Data Science & analytics team using big data tools & frameworks like PySpark, Azure Data Factory & Azure Databricks, causing 33% enhancement in data flow efficiency

Crafted and deployed scalable ETL workflows in Azure Data Factory, facilitating seamless data ingestion from various sources, including Amazon S3 & Azure Blob Storage, into Azure Data Lake (ADLS Gen2) delivering 100% efficiency.

Mastered the management and surveillance of Azure Data Factory (ADF) data pipelines, attaining a remarkable 99% uptime rate, thus guaranteeing superior reliability and peak system performance.

Catalyzed enhancements in the data quality check framework and spearheaded optimization of Spark applications, reducing 28-man hours per activity through strategic data partitioning and advanced caching methodologies.

Conducted thorough data analysis with Spark SQL & PySpark DataFrame API, delivering key insights and clear reports to stakeholders through effective communication with 100% consistency.

Documented and conducted training sessions on data pipelines and data models, sharing expertise with team members and stakeholders.