As a data scientist, I constantly strive to develop new skills and leverage emerging technologies in order to build, validate, and scale mathematically rigorous and efficient solutions to data-oriented problems. While I am deeply technical, I have a strong ability to explain concepts at a high level, both verbally and in writing, and frequently present data science solutions to senior leaders overseeing large organizations. Currently, I am working on an agile software engineering team which is building a computer vision platform to aid in the inspection of utility assets. My objective is to build YOLOv3, Faster R-CNN, and Single Shot MultiBox Detector object detection models, as well as ResNet classifiers, which can be formed into pipelines that identify photographed components in poor condition. After fine-tuning the deep learning models on Amazon SageMaker, I deploy them as microservices through the Seldon Core framework on a Kubernetes cluster. In the past, I have developed, tested, documented, and maintained a large code base of feature engineering pipelines which process over 1 trillion energy usage observations and engineered semi-supervised machine learning models that enhance customer targeting.
I build data products which utilize deep learning, classical machine learning, and optimization solutions in enterprise environments. I have deepened my knowledge of AI with relevant coursework from educational institutions at the forefront of research in this area.
I am experienced at developing RESTful web services, bootstrap dashboards, and other software applications to support business needs. Through CodePath's Android Bootcamp, an eight-week program for experienced engineers, I was able to expand my software engineering knowledge by learning the fundamentals of Android development.
The database technologies I am familiar with include Redshift, Teradata, Oracle, Postgres, MySQL, and Microsoft SQL Server. I often build ETL pipelines, finely tuned queries, and relational data models as well as implement their physical representations to support efficient querying.
I utilize Amazon Web Services (AWS) to build data products with deep learning libraries such as TensorFlow, Keras, PyTorch, and Scikit-learn as well as distributed computing frameworks including Apache Spark. I have also engineered deep learning solutions on the Google Cloud Platform in educational settings.
I frequently present data science solutions to large audiences of director and executive-level leadership, and have taught an eight-week introductory Python class to over 70 of my colleagues at PG&E. Additionally, I presented my innovative research in feature engineering for electric interval usage data at the Association of Edison Illuminating Companies conference in Lake Buena Vista, FL, where I was selected as the highest-rated presenter.
As a data scientist at Pacific Gas and Electric, I have interfaced with business clients to gather requirements, built project timelines and feature release schedules, managed project dependencies and data acquisition, defined piloting scenarios, and brought data products successfully into production. My undergraduate education in Industrial Engineering and Operations Research has equipped me to assist organizations in making effective decisions under uncertainty.
For a complete list of skills, please reference my LinkedIn.
March 2019 - Present
In my current project, I am addressing the important issue of wildfire safety. This project entails developing computer vision models for transmission asset inspection.
August 2017 - March 2019
I focused on customer-centric problems which required data mining over one trillion energy consumption records and building both semi-supervised and unsupervised learning models. During my tenure, I was able to present my research, "Feature Engineering for Time-Series Electric Interval Usage Data," at the Association of Edison Illuminating Companies conference in Lake Buena Vista, FL, and was honored as the highest-rated presenter.
August 2015 - July 2017
I developed professional software engineering skills by collaborating with senior-level engineers to build RESTful web services. I was also able to work on a variety of interesting machine learning projects, learned the Spring and Django web frameworks, and challenged myself to enhance open-source code bases with functionality required for my team's projects.
June 2014 - August 2014
My time at Hyundai afforded me the opportunities to assess, formulate, and implement solutions to a number of intriguing problems, including supply-to-line vehicle route optimization and inventory level optimization. I also developed a cost-savings strategy projected to save Hyundai between $90,000 and $420,000 annually and interfaced with teams from across the plant when designing the process improvement.
August 2011 - May 2015
While majoring in Industrial Engineering and Operations Research at the University of California, Berkeley, I engaged in a number of enriching activities including working on research with professors and graduate students, learning about industry through an engineering internship with Hyundai, leading the Institute of Industrial Engineers, instructing Engineering 98, lab assisting for CS 61B, and working as a Residential Computing Consultant in the dorms.
Additional coursework completed in computer science
While working full time, I engaged in Stanford's graduate-level computer science classes focused on machine learning, artificial intelligence, and data mining.
CodePath's incredible eight-week Android development bootcamp enabled me to deepen my software engineering knowledge by learning the fundamentals of Android development.
I would love to hear from you! The best way to contact me about relevant opportunities is through LinkedIn.