Experienced Machine Learning and Data Science Professional, currently @ Meta
As an accomplished data scientist and mathematician, I bring a wealth of experience and a strong educational background, including a Ph.D. in Mathematics and an M.S. in Statistics. My career has spanned significant roles across leading organizations such as Meta, Peacock, SeatGeek, The New York Times, and Plated, where I have spearheaded numerous initiatives that leverage machine learning and data science to drive strategic decisions and foster innovation. At Peacock, I served as the Senior Manager of Data Science, leading a cross-functional team to implement machine learning-driven pricing strategies that significantly boosted customer lifetime value. My role involved close coordination with teams across Data Science, Product, Engineering, and Promotional Strategy, showcasing my ability to lead and innovate within interdisciplinary teams. My work at SeatGeek as a Lead Data Scientist further honed my expertise in A/B testing, customer experience optimization, and revenue maximization through event-specific pricing strategies. My tenure at The New York Times as a Senior Data Scientist allowed me to develop a diverse array of machine learning models for applications such as churn prediction and sentiment analysis, contributing to the optimization of engagement and dynamic pricing strategies. At Plated, I designed recommendation algorithms and advanced demand forecasting models, enhancing the user experience and operational efficiency. In addition to my professional experience, my academic background includes conducting research on semi-supervised machine-learning algorithms and developing novel techniques for time-series classification, demonstrating my strong foundation in both the theoretical and practical aspects of data science and machine learning. As a mentor, I am eager to share my knowledge and insights with startup founders, guiding them on effectively harnessing data to drive innovation, optimize operations, and accelerate growth. My approach is rooted in a deep understanding of data science's strategic and technical aspects, combined with a passion for mentoring and empowering others to achieve their full potential.
I have extensive experience being the data lead on experimentation teams/pods. This involves working with product to scope and size ideas, designing robust and well-defined experiments, implementing experiments using common frameworks, and interpreting the results. For more advanced applications, I have a deep understanding of both contextual and non-contextual bandits, bayesian statistics, and applying machine learning to conversion flows.
I have worked in Data organizations for my entire tech career. Before that, I studied theoretical data science and machine learning concepts in my PhD program. I'm able to bring together my theoretical and practical experience to help you decide when a data science solution is appropriate for your problem, what sort of approach is warranted, and how it should be implemented.
I believe that while we shouldn't completely discount our intuition, ideas should be validated through rigorous experimentation when possible. This involves making clear assumptions, running planned experiments, and knowing what decisions will be changed based on the results.
I am passionate about experimentation. I have experience working on stand-alone data analytics teams as well as on embedded pods with designers and engineers. My experience has taught me how to design useful tracking analytics, best practices for experimentation design and process, how to determine if a product effect is noise or actual lift, and how to design a roadmap to prioritize experiment ideas. I'd love to chat with you about this!
I have worked with Python extensively in all of my roles since entering industry as a Data Scientist. I am familiar with common packages (pandas, numpy, sklearn, xgboost, keras etc.), object oriented programming, and building backend applications using Python.
I've worked to implement AI solutions across large and small organizations. Whether you are looking to implement recommendations, churn modeling, or bandits, I can help!
Developed and advanced large-scale ranking and prediction models that power Meta’s advertising platform across direct-response and brand objectives. Improved model accuracy, calibration, and architecture, resulting in stronger ad relevance and better outcomes for advertisers. Mentored engineers and collaborated across functions to set and meet strategic goals.
- Lead and collaborate with cross-functional teams (product, design, and engineering) to conceptualize, design, and deploy ML models for high-impact initiatives including targeted offers, email promotions, and content targeting. - Architect and implement MLOps pipelines incorporating CI/CD practices, automated testing, and model versioning using Github Actions, Docker, and Kubernetes. - Implement causal models to drive reliable ML products that drive lift to key metrics. - Design, implement, and analyze experiments to test hypotheses and collect data to train ML models.
As a Graduate Teaching Assistant I teach undergraduate mathematics classes in conjunction with Professors and Lecturers. In this role I am either the sole instructor for a course or a supplemental instructor, meeting with students weekly to reinforce material taught by the primary lecturer. I also create and grade testing materials for the courses.
At Method Test Prep I tutored students in SAT, ACT, and high school mathematics material. I gained experience tutoring in one on one, group, and classroom type settings.
This summer position was at a REU (Research Experience for Undergraduates) run by the Mathematics department at the University of Arizona. Here I actively participated in research in Discrete Topology/Geometry. I mainly worked in a group consisting of one to three other undergraduates as well as several graduate students, post-docs, and professors. My group gave several formal presentations about the research we conducted. These presentations include several talks and a poster session.
My primary role as an undergraduate Teaching Assistant was teaching a recitation section in which students learned new material and reviewed material taught by the primary lecturer. In addition, I was responsible for grading and administering tests, quizzes, and homeworks..
