• Participated in two-year software engineering rotation program, with a focus on machine learning and data engineering roles.

• Developed and supported end-to-end machine learning pipelines in Databricks; from data ingestion, feature generation, exploratory data analysis, model training and testing, experimentation, productionizing, and establishing error alerting systems.• Established multiple data ingesting pipelines for streaming data and relational databases (e.g. Oracle). • Set-up a data acquisition pipeline with a recurring job that sends parallel API calls in PySpark.• Created a new layered model approach that increased overall model precision by 6% and increased lift by 2%.• Led a small team that dealt with creating an XGBoost model to predict different network issues.• Created in-depth business case for indirect savings for machine learning model.

• Created a daily Airflow DAG to send information to marketing on users’ language preferences.• Implemented a retention policy within streaming and batch pipelines to reduce the number of incoming messages.• Overhauled integration tests that create pseudo-data, adding in test cases that were better representative of the data being ingested.• Using Java and Python, added in additional events in streaming and batch pipelines. Monitored and deployed resulting pipelines in Jenkins and GCP.

• Created an algorithm that maps torrent titles to IMDB data using natural language processing in Python, writing finished data to MongoDB.• Presented findings on an XGBoost model and logistic regression model that classified whether a given title was a book, movie, or TV show.

• Performed unit testing on clustering algorithm in SQL and Python.• Worked as the principal ‘App Developer’ for joint internship project that created an application for new rotational hires, developing a full-stack Python Flask application that utilized HTML, CSS, and a PostgreSQL database. Won first place in case competition.

Fall 2019: TA for Statistical Science 101 (Introductory Statistics with R)Spring 2020: TA for Statistical Science 360 (Modern and Bayesian Statistics)Fall 2020: TA for Statistical Science 360

Built a web-scrapper for extracting text as data for future research groups. Funded by Duke's English department, with focus on digital humanities.

Coordinate events for mentors and mentees for David M. Rubenstein scholars.

To understand the connection between presidential rhetoric concerning poverty and policies enacted concerning poverty, utilized R for natural language processing. Continued research in an independent study the following semester, utilizing R and natural language processing to understand sentiment in early English books.

☎️

☕️

🍔