Hi, I'm George

About

I'm a Computer Science student at the University of Michigan. I love exploring applications of machine learning and building scalable systems. I've built production systems as a founding engineer, worked in bank tech, shipped an LLM tool deployed across 26 sites, and published first-author research. Outside of code, I'm interested in philosophy, game design, skateboarding, guitar, and bouldering.

Experience

Building and scaling production systems.

Capital One

Technology Intern

Jun 2026 – Aug 2026

91%test coverage

• Authored 20+ integration tests, lifting service coverage to 91%.
• Architected AWS Lambda data pipelines feeding predictive models.
• Built Python REST APIs with RBAC and parameterized PostgreSQL queries.

AWS Lambda

Python

PostgreSQL

REST

RBAC

BoilerVault

Founding Engineer · Contract

Jan 2026 – Present

2,000+records migrated

• Migrated 2,000+ legacy records via three-tier fuzzy matching — now the production system of record on Railway/Vercel.
• Built a multi-tenant ops platform (FastAPI, PostgreSQL, Next.js/TypeScript) for a 3-campus storage business with JWT auth, RBAC, 20+ endpoints, and 140+ tests.
• Engineered idempotent Stripe webhook reconciliation across 4 accounts and 3 booking sites.

FastAPI

PostgreSQL

Next.js

TypeScript

Stripe

Nexteer Automotive

Software Engineer Intern

May 2025 – Aug 2025

87.5%less code-review time

• Deployed an LLM-powered IDE extension across 26 sites, cutting code-review time by 87.5%.
• Built the extension (Python/TypeScript) to parse 300+ engineering guidelines for automated compliance checks.
• Tuned prompt pipelines to 95% violation-detection accuracy.

Python

TypeScript

LLM

Prompt Engineering

Projects

A mix of systems, ML, and full-stack work. Here are a few I'm proud of.

Architecture

3,000+Jan 2026 - Apr 2026

Wikipedia docs indexed

Scalable Search Engine

A MapReduce pipeline builds a TF-IDF inverted index over 3,000+ Wikipedia documents. A Flask REST index server scores queries with PageRank-weighted cosine similarity across 3 partitioned index segments. A concurrent, service-oriented search frontend dispatches threaded requests to each segment and merges the ranked results. Segments and index servers scale independently for horizontal scalability.

Python

MapReduce

Flask

TF-IDF

PageRank

100+Jan 2025 - May 2025

users served

Resume Screener

NLP pipeline over 1,000+ resumes and job postings. scikit-learn and TensorFlow ranking models with sentence-transformer embeddings and RAG, deployed via Streamlit to 100+ users.

Python

scikit-learn

TensorFlow

RAG

Streamlit

GitHubLive Demo

Skills

Education

Research