I’m a recent graduate of the Duke University Class of 2018, where I earned a B.S. in Computer Science and a B.S. in Statistical Science. Since then, I’ve moved to California, and I currently work at Apple as a Research Engineer on the Apple Media Products Analytics Engineering team.
Highlights: hummus aficionado, bagel snob, future proprietor of a cauliflower farm.
Probabilistic Machine Learning | Statistical Computing | Design & Analysis of Algorithms | Software Design & Implementation | Operating Systems | Introduction to Databases | Bayesian & Modern Statistics | Statistical Case Studies | Statistical Decision Analysis | Statistical Inference | Regression Analysis | Probability | Algorithms & Data Structures | Computer Architecture | Discrete Mathematics | Linear Algebra | Multivariable Calculus
Exclusive development program to strengthen technical skills, through an online technical development curriculum and final programming project. Program culminates in an all-expense paid summit at Google in August 2016. Matched with a Google mentor to participate in mock interviews and meet regularly with throughout the program.
Apple Media Products Analytics Engineering | Research Engineer (2018)
Responsible for collecting requirements from data scientists and business teams and translating them into engineering specs. I develop datsets, machine learning features, and libraries, and I apply them to analytics and research that improve Apple media products such as Podcasts, Apple Music, etc.
AT&T Research Labs | Research Intern (2017)
Conducted research in the domain of Software Defined Networking (SDN), with machine learning applications. Developed an automation tool (full-stack) for day zero configuration and set up of Virtualized Network Functions (VNF) using optical character recognition (OCR) and long short term memory (LSTM) neural networks. Applied convolutional neural networks (CNN) to support an internal facial recognition tool for secure, multi-factor authentication.
AT&T Big Data | Technical Intern (2016)
Carried out data-driven analyses of employee productivity and developed solutions for workflow automation processes and resource management, using graph database Neo4j and other statistical tools. Aided in key decision making processes that resulted in a XX% increase in employee productivity.
Duke CS | Teaching Assistant (2016-2017)
Worked as a TA for Computer Architecture. Responsibilities include holding weekly office hours (both in-person and online), teaching lab sections, and grading assignments and exams.
Selected to work alongside Duke Medical School and BME faculty to better understand the potential risks associated with healthcare centers, environmental microbes, and infectious diseases through mapping the distribution of antibiotic-resistance genes across the Duke campus. Led the computational team in developing tools for data analysis and dissemination. Personally set up data pipeline and developed project website.
Assisting Duke CS and Statistics faculty in developing an interactive tool that will improve online big data database query performance analysis through the use of large-scale, multi-level, directed acyclic dependency graphs. Specifically, researching the use of probabilistic reasoning to define an intelligent method of large-scale data-stream collection and analysis.
Selected by the Information Initiative at Duke (i.i.D.) to research risk behavior with the Duke Center for Cognitive Neuroscience. Applied machine learning algorithms such as linear discriminant analysis, random forests, and k-means to predict individual risk behavior preference, culminating in a predictive model 40% more accurate than previously available models.