my work

a PDF version of my resume can be found here: resume

current role

Principal AI Engineer (December 2025 – Present)

Data Scientist, AVP (June 2023 – December 2025)

AI Engineering

Prototype and develop multimodal AI systems for internal and customer-facing use-cases. Build agents that utilize voice AI tools and are powered by LLM techniques such as RAG and careful prompt engineering.
Perform ML model development and evaluation using Python packages such as scikit-learn, TensorFlow, and PyTorch.
Drive innovation as an inventor on 13 AI-focused patents, pioneering ML and NLP methodologies that enhance content generation, security, and evaluation frameworks.

Data Science

Ensemble k-means and affinity propagation clustering methodologies in Python to optimize the selection of training phrases for a transformer-powered customer-facing chatbot, decreasing the chatbot’s error rate by 58%
Tune classification thresholds to attain a successful classification rate of 94% for a chatbot that receives millions of messages annually

Leadership

Manage and mentor a junior data scientist, fostering skill development and independent project execution
Serve as team leader in the local office, overseeing the work and development of nine teammates

Data Cleaning + Feature Engineering

Utilized advanced programming and data manipulation techniques to clean messy web, account, and product datasets
Applied advanced feature engineering techniques to enhance model interpretability

Segmentation Analysis + Regression Modeling

Segmented customers to determine optimal strategies for maximizing customer retention
Developed interpretable binary logistic regression models in Python for different customer segments using clickstream and account activity data to determine the key performance indicators (KPIs) of customer success

Visualization + Actionable Recommendations

Designed and deployed a Tableau dashboard visualizing KPIs and customer segments
Crafted actionable recommendations of products and discounts to offer customers at various stages of the customer journey
Collaborated with GoDaddy’s product and marketing teams to create tailored plans for each customer segment

Data Scraping + Cleaning

Scraped rating history of the top 1,000 users on letterboxd using the Python library Beautiful Soup
Joined rating history with movie metadata from the Open Movie DataBase (OMDB)
Dropped films with few views and adjusted ratings using z-scores to account for individual rating biases

Memory-Based Recommenders

Generated dense vector embeddings for each movie using SBERT (all-MiniLM-L6-v2) and computed the weighted averages to create personalized user profiles
Performed user-user content-based filtering to recommend movies a user hasn’t seen yet

Model-Based Recommenders

Performed grid-search to fine-tune a Singular Value Decomposition (SVD) model
Combined user and movie embeddings via a deep neural network and predicted ratings with a fully connected architecture using ReLU activations

AWS Certified Cloud Practitioner

AWS Certified AI Practitioner

Institute for Advanced Analytics at NC State University, April 2023

UNC Chapel Hill, May 2022

UNC Chapel Hill, May 2022