Portfolio

Developed and maintained a proprietary Python framework designed internally to streamline and standardize machine learning model deployments across environments for business-critical applications at enterprise scale.

Led the technical development of a cloud-native platform enabling AI developers to seamlessly deploy and orchestrate intelligent agents focused on enhancing developer workflows, including automated code review, technical debt identification, and development process optimization.

Built predictive models to optimize customer interactions, such as predicting call center inquiries and recommending suitable tariffs. Refactored an existing application to enhance maintainability and performance.

Developed applications for revenue assurance processes with SOX compliance and created dashboards to provide actionable insights to stakeholders.

Led the development of an automated data pipeline to support customer's Azure Data Warehousing needs, reducing manual ETL efforts by 80%.

Designed and implemented predictive machine learning models that improved the accuracy of customer engagement strategies for a leading telecommunications client.

Developed, migrated, and operated over 150 system-critical analytical applications from on-premise to Azure, consulting on infrastructure changes and ensuring smooth operations.

Part of a core team that designed and developed an in-house Python framework to streamline and standardize the deployment of machine learning models across environments.

Developed a professional-grade tool for parsing and extracting insightful features from Heroes of the Storm replay files. The tool was tailored for professional use and created in collaboration with an e-sports league to support analytics and strategic decision-making.

Developed a feature-engineering tool for biomolecular simulations to accelerate data analysis during master's and PhD research, significantly optimizing feature extraction for large-scale simulations.