Zane Luis
CS student at University of Michigan building production-grade AI systems. From multimodal pipelines to real-time backends — I ship things that work.
About Me
I build AI systems, not just demos.
I'm Zane Luis, a sophomore studying Computer Science at the University of Michigan. I transferred from Penn State where I made the Dean's List, and before that grew up in Dubai, UAE — graduating with a 90% ISC aggregate.
My focus is on the intersection of AI and systems engineering: building pipelines that are production-ready, not just proof-of-concept. I care about latency, correctness, and the tradeoffs behind every architectural decision.
Currently diving deep into LLMs, RAG, and model fine-tuning alongside my coursework. Outside of code, I captained a varsity basketball team and taught Java remotely to students in Kenya.
98/100
CS Score @ GMA
Dean's
List @ PSU
2027
Target Internship
2+
Prod. AI Systems
Honors & Awards
Silver Award — Duke of Edinburgh (UK), 2025
School Runner-Up Computer Science — 98/100, GMA 2025
Math Olympiad (GIMO) — International Rank 739, 2024
Projects
Things I've shipped.
A full-stack dating app with a multimodal AI compatibility engine — combining facial feature analysis, personality alignment, and interest matching into a single normalized score.
Multimodal AI pipeline using Claude Vision API with a 40-label controlled vocabulary — zero label drift via structured prompting + server-side validation
Four-signal compatibility engine: Jaccard similarity (40%), personality (20%), facial preference matching (30%), mutual attraction bonus (10%) — O(n) ranking per request
Production FastAPI backend: 6 domain-separated routers, SQLAlchemy ORM, JWT/bcrypt auth, email verification, bidirectional block filtering, 200 req/min rate limiting
Real-time WebSocket chat scoped to matched pairs, Framer Motion swipe UI with rAF pause on visibility loss, PWA installability for iOS & Android
Snake & Ladder Engine
AcademicPSU CMPSC 132 Final Project
A fully playable Snake & Ladder game built from scratch using object-oriented design principles and core data structures — implemented as a Penn State CMPSC 132 capstone.
Designed with OOP principles: Player, Board, Snake, Ladder, and GameEngine classes with clear encapsulation and single-responsibility boundaries
Board represented as a graph-adjacency structure; snake/ladder jumps modeled as directed edges enabling O(1) position lookup
Implemented custom queue for turn management and stack-based move history for undo functionality
Clean separation of game logic from display layer, making it trivially portable to CLI, GUI, or web rendering
NBA Prediction Bot
PyTorch · ESPN API · Kalshi API
More AI Projects
Building Summer 2026
Skills
Tools of the trade.
Languages
AI / ML
Backend
Frontend
Developer Tools
Experience
Where I've worked.
Data Analytics Intern
Samsonite
- Analyzed sales performance data to evaluate growth opportunities for the American Tourister Airconic product line
- Assessed target markets, pricing ranges, and consumer segments to inform product development strategy
- Built visual dashboards in Google Looker Studio to communicate findings to stakeholders
Product Development Intern
Cult.fit
- Designed a fitness mobile app MVP aimed at making health and wellness more accessible
- Conducted market research to identify user pain points and define a clear problem statement
- Translated insights into a user-centric MVP design
Remote Java Coding Instructor
Kyangala Girls High School, Kenya
- Taught Java programming remotely to underprivileged students as part of a Duke of Edinburgh Award volunteering project
- Designed and delivered lessons covering programming fundamentals, logic, and problem-solving
- Several students expressed interest in pursuing STEM — bridged geographic and cultural gaps through sustained remote mentorship
Head of Web Development
Debuggers Club
- Led development of a centralized database system to digitize the school House Points System
- Built and maintained full-stack web applications (HTML, CSS, React + PHP, MySQL, Apache)
- Designed a device tracking system for school-owned hardware
Member — Machine Learning
ML @ Penn State
- Built a Python text sentiment classifier using Keras at the Cursor & MCP Showcase
- Participated in workshops on ML fundamentals, clean code structure, and rapid prototyping with AI-assisted tools
Let's build something together.
I'm actively looking for AI Engineering internship opportunities for Summer 2027. If you're working on something interesting, I'd love to talk.
Say HelloBuilt with Next.js & Tailwind · 2026 Zane Luis