About me

I am a data scientist with experience in applied statistics, machine learning, data engineering, and software development.

My background

I earned my Master’s in Statistics at Baruch College, where I studied machine learning and worked on projects that focused on natural language data.

During my studies, I had the opportunity to work at Phosphorus, a biotech startup where I led the company's effort to extract meaningful insights from operational data. My collaboration with the COO and laboratory manager resulted in a substantial reduction in laboratory sample turnaround time by 75% while we scaled our business by double.

After Phosphorus, I joined Govini as a data engineer, where I supported the launch of the company's flagship product, Ark.ai.

Ark.ai is an AI-powered platform that helps government agencies make better decisions using data. I built ETLs using AWS Glue and used Spark to perform data operations on massive datasets, often over 100 million rows.

I took some time after Govini to work full time on Sunbelt, a project to crawl natural language data from publicly available APIs and store them in a database. These data are accessible via a GraphQL API and an open source python api wrapper.

I leveraged this experience towards my current role as a data scientist at /prompt, a marketing agency, where I focus on innovation projects such as using NLP to analyze social media data. Specifically, one of my most recent projects focused on building document clusters using Doc2Vec embeddings and HDBSCAN, and using prompt engineering to create a hierarchy of descriptive topic names from the hundreds of resulting clusters. I also created a proprietary extension for Top2Vec that enhanced the topic modeling workflow for our team.

Contact

If you are interested in learning more about me or my work, please feel free to contact me at my email below, or connect with me on LinkedIn. You can also check out my GitHub for some of my projects.