Michael Marin
Michael E. Marin, ML Engineer

Building production AI systems with measurable impact

Open to ML Engineer and AI Product roles

I turn research-grade ML ideas into things people can actually use — real-time interfaces, LLM-powered products, and agentic tools. Currently building agentic AI at Mr. Cooper Group while finishing an M.S. in Artificial Intelligence at UNT (Expected May 2027).

dallas, tx

0

In-browser ML demos

live in the ML Lab below

0+

Test assertions

SIMLYFE engine + LLM modules

0

Person team led

NASA PACE capstone exhibit

0

M.S. AI

expected — UNT, ML focus

michael@dallas — zsh

$ whoami. ml-engineer — dallas, tx. $ current_focus. → agentic AI @ Mr. Cooper. → M.S. AI @ UNT (May 2027)

$ cat about.md

About Me

I'm Michael — an ML engineer based in Dallas who got hooked on AI the moment I realized a model could turn messy, real-world data into something people actually understand. I studied Computer Science Engineering at the University of North Texas, stuck around for a master's in Artificial Intelligence, and I help run the UNT AI Club as its treasurer. Whether it's a NASA satellite exhibit, an LLM-driven game, or an agentic tool at work, what I care about most is the moment an idea stops being a notebook and becomes something someone can actually click.

ML engineer focused on production AI systems — real-time interactive visualization, LLM-powered products, and the evaluation discipline that keeps them honest. Led a 5-person team building a NASA PACE satellite-data exhibit shown at the Kennedy Center in Washington, D.C., and shipped SIMLYFE, an LLM-driven life simulator with 350+ automated test assertions. Currently pursuing an M.S. in Artificial Intelligence (ML focus) at the University of North Texas while building agentic AI products at Mr. Cooper.

Selected work

Flagship Projects

A national research exhibit and a shipped, LLM-driven product.

01 / NASA PACE · University of Maryland IMD · University of North Texas · Jan 2024 – May 2025

Wave: From Space to Ocean (NASA PACE Capstone)

The problem

NASA's PACE mission produces large-scale, high-dimensional oceanographic and atmospheric satellite data that is difficult for non-experts to interpret or interact with. The goal was to transform raw satellite data into…

The build

Led a team of 5 building an interactive, gesture-driven exhibit visualizing live data from NASA's PACE satellite.

C#
C++
Python
Unity
OpenCV
ZED SDK
+6 more
Read the case study
Kennedy Center, Washington, D.C.
  • → Premiered March 2025 · national museum tour planned
  • → Led a 5-person capstone team
  • → ~70% setup-time cut via automated calibration wizard

02 / Personal Project · 2025 – 2026

SIMLYFE: LLM-Driven Life Simulator

The problem

LLM-generated content is compelling but unreliable: left unconstrained it breaks game-state coherence, and calling it naively from the browser leaks API keys. The challenge was building a playable, shippable game where…

The build

Built and shipped a mobile-first, browser-based life simulation game where players age a character year by year through careers, relationships, finances, and procedurally generated life events.

React 19
TypeScript
Vite
Supabase Edge Functions
Firebase
OpenAI GPT-4o-mini
+2 more
Read the case study
Live in production
Live DemoRepository

350+ automated test assertions · Vitest

Interactive ML Lab

Real algorithms running in your browser — not videos.

Real in-browser inference — a convolutional net served with onnxruntime-web, the same pattern used to ship ML to the edge.

Track record

Experience & Projects

  1. May 2025 – Present

    Product Analyst Intern, AI/ML team

    Mr. Cooper Group

    • Selected for a competitive 10-week internship with the Product Management AI/ML team.
    • Contributing to the development and support of internal Agentic AI products to help automate customer service.
    • Responsibilities include story writing, user testing, model evaluation, and cross-functional collaboration with design, engineering, and business units.
    Details

  2. 2025 – 2026

    SIMLYFE: LLM-Driven Life Simulator

    Personal Project

    • Built and shipped a mobile-first, browser-based life simulation game where players age a character year by year through careers, relationships, finances, and procedurally generated life events.
    • Integrated GPT-4o-mini as a life-event generation engine behind a server-side LLM proxy, keeping API keys off the client entirely.
    • Engineered deterministic game systems (economy, career ladders, relationship dynamics) that blend with LLM-generated narrative events.
    Details

  3. Jan 2024 – May 2025

    Wave: From Space to Ocean (NASA PACE Capstone)

    NASA PACE · University of Maryland IMD · University of North Texas

    • Led a team of 5 building an interactive, gesture-driven exhibit visualizing live data from NASA's PACE satellite.
    • Built full-stack applications integrating cloud data pipelines for large-scale scientific computations, with React/TypeScript visualization layers.
    • Designed a Setup Wizard using ImGui and OpenCV that cut exhibit setup and calibration time by roughly 70%.
    Details

Capabilities

Technical Skills

Programming Languages

Python
TypeScript / JavaScript
C++
SQL

AI/ML & Data Science

PyTorch
TensorFlow
OpenCV
NLP
RAG Pipelines
BM25 & Cross-encoder Reranking
LLM Evaluation
Scikit-learn

Cloud & DevOps

AWS
Google Cloud (Vertex AI, BigQuery)
Docker
Kubernetes
GitHub Actions
CI/CD pipelines
Linux

Backend

FastAPI
Node.js
PostgreSQL
pgvector
Redis
Flask
Firebase
RESTful APIs

Frontend

React
Next.js
Tailwind CSS
Data Visualization

Academic foundation

Education

Pursuing a master's in AI while shipping production systems.

Expected May 2027

MS, Artificial Intelligence (Machine Learning Focus)

The University of North Texas (UNT)

Current coursework

Applied Artificial Intelligence
Advanced Machine Learning
Graduated · May 2025

BS, Computer Science Engineering

The University of North Texas (UNT)

GPA 3.25 (4.0 Scale)

Beyond the classroom

Treasurer of UNT AI Club (2023–Present) — led AI/ML workshops and hackathon participation.

Third-party proof of the NASA PACE exhibit

Independent Coverage

UMD College of Computer, Mathematical & Natural Sciences

WAVE exhibit premieres at the Kennedy Center

Coverage of the NASA PACE 'Wave: From Space to Ocean' exhibit premiere in Washington, D.C.

Read coverage →

UMD Immersive Media Design

WAVE: New understanding about Earth's oceans and atmosphere

Feature on the interactive satellite-data exhibit built with the NASA PACE team and UNT capstone students.

Read coverage →

NASA PACE Mission

WAVE: From Space to Ocean

The official NASA PACE mission page for the WAVE exhibit.

Read coverage →

auto-updates every 6h

Live from GitHub

xmike04.github.io

project website

TypeScriptupdated Jul 2026

SIMLYFE

—

JavaScriptupdated Jul 2026

Get in touch

Let's build production AI together

Open to ML Engineer and AI Product roles — full-time or contract.

Dallas, TX