Hudson Pagni
I build data systems that turn raw numbers into clear decisions, from machine learning simulations to analytics that run at scale. I am working toward a career in data analytics and data engineering.
A little about me
- Education
- B.S. Statistics & Data Science, UCLA
- Graduating
- June 2028
- Focus
- Data Analytics & Data Engineering
- Based in
- Los Angeles, California
I grew up in San Diego, California, where I went to La Costa Canyon High School and earned my IB Diploma. I have loved statistics and data since I was young, and in high school I turned that interest into a research paper on gender bias in college admissions. Today I study Statistics and Data Science at UCLA, with an expected graduation in June 2028. I am aiming for a career in data analytics or data engineering, building systems that turn raw data into clear decisions. My favorite and most complex project so far is a Counter-Strike 2 system that trains AI versions of professional players, simulates full matches, and prices live betting markets on Polymarket. When I am not working on projects or coursework, I am a diehard Padres fan.
Featured projects
Counter-Strike 2 Dream Team: Cloning the Pros to Build the Perfect Roster
A machine learning system that clones professional Counter-Strike 2 players from their real matches, proves each clone is genuinely that player, simulates full matches between them, and searches tens of thousands of lineups for the team that plays best together.
View project
Instagram Automation and Analytics Platform
A distributed platform that operates a large fleet of Instagram accounts from one place, generates their content with AI, and tracks engagement across the whole network.
View project
Autonomous Multi-Agent Roblox Game Studio
Two complete Roblox games built by fleets of AI agents over a Roblox Studio MCP toolchain, with me as architect and orchestrator: specs of record, frozen inter-agent contracts, and headless verification gates that let each agent prove its own Luau before it was accepted.
View project
rsi2bot: An Agentic Trading Safety Engine
A paper-by-default equities trading agent for the official Robinhood Agentic Trading MCP server, built on the premise that an LLM-accessible broker is a hostile surface: fail-closed live gating, a disk-persisted kill switch, hard cost gates, and a 43-test suite that asserts the safety invariants.
View project
AI RVC v2 Voice Modeling
An end to end voice conversion pipeline that trained and publicly released more than ten voice models.
View project