Building the pipeline. Building the model.

Developed and evaluated predictive models — including Random Forest, Neural Networks, and Deep Neural Networks (BigQuery ML) — to identify at-risk students, enabling earlier intervention and improved decision-making. Engineered behavioral features from LMS and SIS data including engagement trends, activity rates, and temporal signals used directly in production models.

Owned end-to-end development of a production-grade analytics pipeline using dbt (32 models) in BigQuery, transforming raw institutional data into analytics-ready feature marts supporting both modeling and stakeholder reporting. Implemented data quality testing and validation within dbt to ensure reliability and trust in downstream use cases.

Migrated consultant-built ML applications into GCP-native environments using Vertex AI, Docker, and Cloud Workstations, improving reproducibility and scalability. Modernized institutional reporting by refactoring legacy stored procedure logic into warehouse-native SQL, integrating Python-based statistical analysis, and building a Looker dashboard supporting leadership — recognized with the UCR STAR Award (February 2026).

Co-founded boutique data science consultancy delivering machine learning solutions, predictive modeling, and advanced analytics across research and data-driven organizations.

Co-developed the EDA Toolkit, a production-grade open-source Python library for exploratory data analysis and statistical workflows, under contract with Taylor & Francis (anticipated publication late 2026/early 2027). Presented EDA Toolkit at JupyterCon 2025 alongside collaborator Leon Shpaner (UCLA Health), demonstrating reproducible analytics pipeline design to an international audience.

Facilitating coursework in applied data engineering with focus on pipeline design, ingestion workflows, and data quality best practices. Guiding students in designing production-oriented data workflows using SQL and cloud-based data platforms; evaluating student-built pipelines for reliability, scalability, and validation rigor.

Designed and maintained large-scale ETL pipelines and analytics workflows supporting enterprise reporting and operational decision-making across the district. Built scalable star schema data models to support cross-functional analytics use cases across multiple source systems.

Developed dashboards and reporting solutions (SSRS) for operational and executive stakeholders; optimized SQL queries and BI infrastructure to improve performance and reduce latency. Led stakeholder sessions to translate business requirements into structured analytical solutions and reporting frameworks.

Developed ETL pipelines integrating multiple data systems using SQL, SSIS, and Python; built reporting solutions and automated workflows supporting business operations. Maintained and supported SQL Server-based data infrastructure, improving data accessibility and consistency across the organization.

Project lead for student information system migration. Scoped infrastructure requirements (VPN, SFTP, SQL Server), set up database restore processes from remote servers, and authored migration scripts that successfully transferred all student records.

Diagnosed and resolved student information system issues using SQL, Access, and Excel. Assisted clients with data extracts meeting vendor file layout specifications.