Home

Career Journey

My adoration for Data Science didnt really begin as much as my many interests and curiosities slowly converged to one field. From my statistics and computer science course work to the first time I wrote a script to the many research papers I've read, I've slowly learned what I find interesting and what I'm best at. While at Ohio State, I built a strong foundation in Data Analytics and Economics. My experiences in BDAA organizing and conducting student led research, teaching lectures on machine learning and python, and taking on leadership roles gave me a wide berth of organizational experiences. While conducting research with Dr. Christian Blanco and Dr. Tanya Berger-Wolf, I learned what it meant to formulate a problem space and develop a plan to understand its inner workings. My business analytics internship at Amazon taught me how to operate in a massive organization and that I missed the science of data science. When moving to JPMorgan Chase I realized how fun becoming an expert in a subject was and how to advocate for the projects I believed in. All of this solidified my passions for Data Science and developing cutting-edge AI and machine learning solutions, from anomaly detection workflows to tailored LLM tools. Now, as I pursue my Master's in Computer Science at Georgia Tech, I am excited to continue deepening my expertise and tackling the next generation of challenges in AI.

Interests

Currently, I am deeply fascinated in understanding how pre-trained genrative systems "think", how we can use math to measure and comprehend their latent understanding space, and how they will develop over time.

Experience

AI R&D Data Scientist

Proposed and developing an Agentic AI solution to ingest business needs from Jira’s MCP, propose a plan, orchestrate agents and tools, write playwright test scripts, self heal errors, and report outcomes in order to automate UI integration testing, a monthly 20-hour task.
Researched and implemented Autoencoder, LOF, and IF anomaly detection models; explainable AI concepts including SHAP and LIME analysis; and Pareto optimality for multi-objective optimization to support an ensemble learning approach on multiple financial data sets, the current solution is a 12% improvement on existing systems.
Built an internal Metric Store which converts proprietary business logic into SQL based metrics; currently supporting daily refreshes on 130 metrics to 12 downstream controllers, leading to a 70% user compute use reduction and 80% query speed increase.
Converted high complexity data investigation tasks into learnable logic to be fed into Databricks Genie spaces, providing a tailored LLM based data analytics tool to ease business user workload
Presented multiple internal webinars explaining topics such as Databricks, anomaly detection, and data engineering to groups of 20 to 100 people.

AI & ML Data Science Intern May 2023 – Aug. 2023

Developed a 6 model ensemble anomaly detection workflow to check millions of daily trade contracts for upstream errors in the data engineering pipeline.
Built a data quality process to check the accuracy of incoming and outgoing data streams to support the transition of data pipelines, automating a daily 30 minute task.

Research Assistant

Contributed to published research showcasing the financial impacts of illegal and unsustainable business practices.
Utilized OpenNLP for named entity extraction, topic modeling, and sentiment analysis on 100k documents over 40 years.

Data Analytics Intern

Discovered 500 unresponsive or poor response medical prompts which when routed to our product leads to a boost of 250 to 500 thousand monthly active users.
Performed customer segmentation analysis on the Alexa Health user base and presented my findings to management.
Took over a root cause analysis task after our Business Intelligence Engineer left the team, identified the cause of a metric discrepancy and reworked the SQL query in the ETL pipeline to prevent future errors.

Education

Masters of Science in Computer Science Jan. 2025 – May 2027

Bachelor of Science in Data Analytics; Minors in Economics, Computational Analytics Aug. 2020 – May 2024

Projects

Currently I am using toy models to better understand concepts such as Superposition and Branch Specialization.

Developed Time Series Classification models using Convolutional and Recurrent Neural Networks to single out and determine the status of airplanes at the KOSU airport. Completed under Dr. Tanya Berger-Wolf.