Jared Yu Email & Phone Number

California, United States

Cupertino, California, Us

• Designed and implemented a scalable ELT pipeline utilizing Kubernetes, S3, Iceberg, Trino, Kafka, Flink, Airflow, Spark, and Snowflake for terabytes of lab data, optimizing resource utilization by saving 10+ hrs/week on compute and enabling data scientists to focus on high-value tasks. Enhanced pipeline efficiency through custom logging and monitoring, facilitating rapid debugging. Developed insightful Tableau dashboards for data visualization. Managed the maintenance and operations of the lab instruments and data processing. Held scrum meetings for projects that there was ownership of, keeping stakeholders up to date on the progress of tasks.• Improved data quality and cost efficiency by building an automated anomaly detection pipeline in Spark and Snowflake, saving 6+ hrs/week in manual work. Streamlined processes further by creating a web-based maintenance dashboard in Streamlit for quick issue identification and resolution.• Constructed a KPI dashboard and ELT pipeline using Kubernetes, Airflow, Spark, Snowflake, Plotly, and Streamlit for user data, empowering users to take data-driven actions based on key metrics and set thresholds. Increased user productivity through improved data observability.• Enhanced user experience and data ecosystem transparency by implementing a data catalog and data lineage solution. Elevated data quality by establishing a data validation pipeline using the write-audit-publish pattern utilizing data contracts, data drift detection, and a comprehensive summary statistics dashboard for continuous heuristic refinement.• Leveraged statistical analysis using methods such as regression, clustering, and dimension reduction to identify anomalies and gain deep insights from complex user datasets. Impacted various problem areas through a diverse portfolio of statistical, machine learning, and deep learning models built with PyTorch, TensorFlow, scikit-learn and other machine learning libraries.

San Francisco, California, Us

• Authored blog posts for an online community of data scientists, garnering over 25,000 page views in total (https://www.kaggle.com/code/yuqizheng/neural-networks-for-beginners-math-programming). Developed clear and concise explanations of complex data science concepts that can be understood by a broad audience.

Oakland, California, Us

• Developed and implemented an ETL pipeline using Python, SQL, Power Query, DAX, M, and VBA to automate weekly and monthly KPI reports for Excel and Power BI dashboards. This reduced report delivery time by over 80%, ensuring data quality through downstream QA/QC checks. Scripted data processing tasks in Python for colleagues, improving efficiency and minimizing manual errors.• Performed data analysis, generating novel insights delivered in comprehensive reports with visualizations using Python and Power BI. Designed interactive dashboards to transform complex data into clear visuals, allowing for actions to be taken by stakeholders.

Mountain View, California, Us

• Designed and implemented metrics for evaluating self-driving car performance in diverse scenarios using in-house software frameworks. Developed SQL queries to generate scenarios to be distributed to team members. Utilized Jira for tracking the progress of various tasks.

Master Of Science - Ms, Data Science (Honors)

Bachelor Of Science - Bs, Statistics