CV

Data Scientist

Invictus Growth Partners

Engineering LLM-powered systems for enterprise data analysis and classification.

• Engineered a novel LLM classification framework to systematically prioritize unstructured data from noisy and incomplete sources.
• Built an end-to-end semantic search system using text embeddings and a custom re-ranking algorithm for highly relevant results.
• Architected a scalable insights engine, using a flexible LLM classifier to operate across diverse business datasets.

AI Training Specialist

DataAnnotation & Outlier AI

Freelance position enhancing AI models and collaborating with development teams.

• Enhanced AI models by correcting coding and mathematical responses, improving accuracy and reliability.
• Identified and rectified hallucinations in AI outputs, contributing to significant error rate reduction.

Graduate Teaching Assistant

University of Colorado Boulder

Assisted in teaching mathematics courses.

• Assisted in teaching mathematics courses including Calculus and Differential Equations.
• Provided academic support and feedback to students.

M.S.

University of Colorado Boulder

Applied Mathematics

• Data Science
• Machine Learning

B.A.

Lake Forest College

Mathematics, Economics

MathBuddy: AI-Powered Math Tutor

Full-stack AI tutor utilizing GPT-4o for interactions and GPT-3.5-Turbo for result extraction and difficulty estimation.

• Engineered a full-stack AI tutor utilized by over 200 users, leveraging GPT-4o for interactions and GPT-3.5-Turbo for result extraction and difficulty estimation.
• Implemented serverless architecture with Next.js frontend and FastAPI backend, integrating OpenAI and Wolfram Alpha APIs to enhance problem-solving capabilities.

Tic-Tac-Toe with Alpha-Beta Pruning

Tic-Tac-Toe game featuring an AI opponent using the Alpha-Beta Pruning Minimax algorithm.

• Developed a Tic-Tac-Toe game featuring an AI opponent using the Alpha-Beta Pruning Minimax algorithm.
• Improved AI decision-making speed by 40% by reducing evaluated nodes, enhancing gameplay experience.

ODE Solution via PINNs

Solved the damped unforced pendulum problem using Physics-Informed Neural Networks.

• Engineered and trained a Physics-Informed Neural Network (PINN) to accurately model the damped pendulum problem, demonstrating the successful application of a cutting-edge deep learning technique to solve complex ODEs.