Ting-Wei Wu

About Ting-Wei Wu

Hi, my name is Walt Wu, and I’m a Software Engineer and Data Scientist who graduated from UT Austin, where majored in Informatics. My expertise spans across a range of programming languages, including Python, SQL, and JavaScript, with a strong focus on data engineering, machine learning, and web development. Throughout my academic journey and internships at Qorvo Inc, Silicon Labs, and the Georgia Tech Research Institute, I’ve gained hands-on experience in developing and deploying data pipelines, automating complex processes, and creating machine learning models that have driven significant cost savings and efficiency improvements. For example, during my recent internship at Qorvo, I developed and optimized data pipelines that integrated trillions of data points, resulting in multi-million dollar savings. I also deployed a CNN model with high accuracy for wafer defect analysis, projected to save an additional hours a week. At UT Austin, my academic projects have allowed me to apply machine learning techniques to real-world problems, achieving high accuracy in predictive models and data analysis. These experiences have solidified my passion for leveraging technology to solve complex challenges and push the boundaries of what’s possible in software engineering and data science. I’m eager to continue growing in roles that allow me to innovate and create impactful solutions. My main focus remains on data engineering, data science, and machine learning engineering, but I’m also enthusiastic about opportunities that intersect with software development. I’m excited about the future and the chance to contribute meaningfully to the tech industry.

Experience

1. Data Science Engineer

   Qorvo, Inc.

   Apr 2024 — Present · Dallas, TX, US

   Developed robust data pipelines integrating over 20 tables and more than 10 trillion data points using PySpark and SQL on Databricks, while creating reusable Python libraries to enhance RF chip yield analysis- Automated manufacturing processes by developing a full-stack web app with an Apache and Flask backend, React.js frontend, and Oracle database integration to reset fabrication alerts, reducing 300 hours of manual work per month- Deployed a CNN for image classification with 99.7% accuracy using TensorFlow, significantly improving wafer defect analysis, and utilized Plotly for 6D feature visualization to identify optimal feature selection- Created Bayesian statistical models in Python and R to optimize sampling, enabling efficient resource utilization and risk management through data science, preventing potential yield loss.Responsibilities- Specific projects and responsibilities will be determined based on the business needs at the time of the internship assignment- Develop, construct, test, and maintain databases and use big data processing systems in support of analytics and applications- Develop and maintain CI/CD data pipelines that unify data acquired from multiple sources- Prepare data for use in diagnostic, predictive, and prescriptive modeling- Analyze data to optimize factory performance, increase yields, and reduce costs- Collaborate with BI users, applications developers, and data scientists to establish and refine requirements for data and analytics

Education

• School of Information - The University of Texas at Austin

  Undergraduate

  2021 — 2024

• The University of Texas at Austin

  Minor

  2021