Skip to content
Michael Rusu
HomeBlogFeaturedProjectsExperienceContactView résumé
Michael Rusu outdoors in front of bamboo

Michael Rusu

I’m an Honors Data Science and Computer Science student at the University of Central Florida.

I’m interested in solving problems using machine learning, mathematics, and data. I like training complex models, running experiments on high-performance computing systems, serving those models, and scaling them.

when I’m not training models, I’m usually playing guitar, hiking, rock climbing, listening to music, or experimenting with hardware.

Blog

Notes from the Work

1 field notes
Complete mixture-of-experts mental model showing the token data path and systems control plane01

Machine Learning Systems · August 2026 · 16 min read

271,104 Routes: What I Missed About Mixture-of-Experts

I pulled 271,104 token-to-expert assignments from an IBM Granite forward pass, then used them to understand what happens after an MoE router returns top-k.

Read article
Mixture-of-ExpertsDistributed MLModel Architecture

Featured

Career Recognition + Technical Work

6 selected features
OpenAI logo

OpenAI Developers · Official Directory · 2026

Codex Ambassadors

Official OpenAI directory recognition as a Codex Ambassador representing the Orlando developer community.

View directory
Intro to Machine Learning workshop thumbnail

Technical Workshop · YouTube · 2026

Intro to Machine Learning with Michael Rusu

An accessible introduction to how machines recognize patterns and learn from the signals around us.

Watch workshop
Ethan Troy logo

Ethan Troy · Event Recap · 2026

OpenAI Codex Community Meetup — Orlando

An independent attendee recap highlighting Michael and the builders shaping Orlando's emerging AI community.

Read recap
Intro to Data Science workshop thumbnail

AI@UCF · Technical Workshop · 2025

Intro to Data Science (Pt. 1)

A workshop appearance covering the foundations of collecting, cleaning, exploring, and understanding data.

Watch workshop
Brain-computer interface research setup

Brain-Computer Interface · Research Paper · 2025

On the Efficacy of a Consumer-Grade EEG Device for Brain-Computer Interface Applications

An evaluation of consumer EEG hardware for BCI applications, connecting signal processing with real-time drone control.

Read paper
Robotic arm used for autonomous food-service research

Machine Learning + Robotics · Research Paper · 2025

AI-Driven Automation in Fast Food: Integrating Large Language Models with Robotic Systems

Research on combining language models, computer vision, and a robotic arm for an autonomous food-service workflow.

Read paper

Projects

A field guide to the machines, models, and products I have built across robotics, AI, and the web.

Browse by discipline

Showing 14 of 14 projects

Open any build for the full notebook

CrisisLens project preview01 Award winner

Data Science

CrisisLens

1st Place Winner at Hacklytics (Databricks x United Nations Challenge). CrisisLens is an AI-assisted crisis intelligence platform that combines real-time geospatial context, ML forecasting, and Databricks-powered natural language analysis to help humanitarian teams prioritize aid decisions.

DatabricksUnited Nations ChallengeNext.jsTypeScriptThree.js
DetailsCodeDemoDevpost
Guido project preview02 Award winner

Robotics

Guido

Autonomous, voice-controlled wheelchair prototype that maps unknown spaces with LiDAR, supports direct spoken movement commands, and uses layered ROS 2 autonomy for safer hands-free navigation.

ROS 2Nav2SLAM ToolboxLiDARNVIDIA Jetson
DetailsCodeDemoDevpost
SimplyLaw project preview03 Award winner

AI Systems

SimplyLaw

1st Place Hackathon Winner - Multi-agent legal AI platform solving the chaos of personal injury case management. Four specialized AI agents collaborate to process messy legal documents (PDFs, audio, scanned faxes), perform strategic case analysis, and draft legally-safe client communications.

Multi-Agent SystemsGoogle-ADKFastAPINext.jsOCR (Tesseract)
DetailsCodeDemoDevpost
FinFluence project preview04

Full Stack

FinFluence

AI-powered financial literacy platform that turns short-form video education into a tokenized economy. Sentence transformers validate content, custom Solana SPL tokens reward engagement. Built at SwampHacks XI.

SwampHacksFastAPISentence TransformersSolanaMongoDB
DetailsCodeDemoDevpost
CSIRO Image2Biomass Prediction project preview05

Computer Vision

CSIRO Image2Biomass Prediction

Kaggle competition for predicting pasture biomass from images using a 4-model stacking ensemble. Achieved 21% MAE improvement over the best individual model with R² of 0.9998.

PyTorchDINOv2ConvNeXtSigLIPStacking Ensemble
DetailsCode
Neighborly project preview06

AI Systems

Neighborly

Neighborly is a mutual-aid app that makes helping local communities simple. Users can offer or request items, services, or time, while organizations can post shortages directly. AI agents highlight the top 3 urgent needs nearby, balance supply and demand, and keep posts safe and trustworthy.

ReactTailwindCSSSupabaseGoogle-ADKPython
DetailsCodeDemoDevpost
Mind-Controlled Drone project preview07

Robotics

Mind-Controlled Drone

Developed EEG-based BCI system to control drone movements. Integrated signal processing with real-time control algorithms.

BCISignal ProcessingHybrid CNN-LSTMMNEPython
DetailsCodePaper
RNA 3D Folding Pipeline project preview08

Data Science

RNA 3D Folding Pipeline

ML pipeline for predicting RNA 3D structures. Used transformer architecture with geometric deep learning for molecular modeling.

BioinformaticsTransformersTensorFlowMolecular MLGPU Computing
DetailsCode
Multimodal Sensor Fusion project preview09

Robotics

Multimodal Sensor Fusion

TensorFlow model integrating IMU, ToF, and camera data for robust perception. Applied in autonomous navigation scenarios.

Sensor FusionTensorFlowClassificationData AugmentationCross Validation
DetailsCode
AI Burger Flipper project preview10

Robotics

AI Burger Flipper

AI-driven fast food automation system that fuses LLaMA 3.1 with a 6-DOF robotic arm for autonomous ordering and delivery. Uses MediaPipe for customer detection, Flask-SocketIO for natural language ordering, and OpenCV vision pipeline for precise burger grasping. Achieved 86% success rate over 50 trials.

Computer VisionOpenCVRoboticsFlask-SocketIOMediaPipe
DetailsPaper
MusicMap project preview11

Data Science

MusicMap

A Flask-based web application that provides artist recommendations using clustering techniques. It integrates with Spotify's API to fetch track previews and related artist information.

FlaskPythonK-Means ClusteringSpotify APIPandas
DetailsCode
Crime Prediction project preview12

Data Science

Crime Prediction

This project aims to predict crime occurrences in Chicago using machine learning techniques. By analyzing historical crime data along with various socio-economic and environmental factors, we aim to build a predictive model that can anticipate the likelihood of different types of crimes in different areas of Chicago.

PythonMachine LearningFlaskscikit-learnRandom Forest
DetailsCodePaper
ST13

Data Science

Stock Prediction

Multi-model ensemble ML system for stock price forecasting using Random Forest, SVM, and Linear Regression. Features Flask backend with real-time progress updates via Server-Sent Events, automatic market hours detection, and optional news sentiment analysis with TextBlob.

PythonMachine LearningFlaskscikit-learnRandom Forest
DetailsCode
VSLAM Drone Navigation project preview14

Robotics

VSLAM Drone Navigation

Monocular Visual SLAM system for autonomous drone navigation featuring ORB and SIFT feature detection, MIDAS depth estimation, and 3D point cloud reconstruction. Implements Structure from Motion (SfM) with Extended Kalman Filter for robust pose estimation in GPS-denied environments.

Computer VisionSLAMORB-SLAMSIFTDeep Learning
DetailsCode

Beyond the archive

Open Source + Community

Contributions to tools and communities I care about.

What I did

  • Completed fixes across streaming, iterable datasets, and packaged modules.
  • Activated upload shard sizing, completed Arrow iteration paths, and fixed archive glob and Pandas feature-casting behavior.
  • Added regression coverage for the updated data-loading and streaming paths.
PR #8068

What I did

  • PR #910 fixed windowed cache updates, reset behavior, and legacy-cache restoration, with regression tests.
  • PR #1051 added heterogeneous hybrid-attention configurations and centralized validation and per-layer lookup across 21 model families.
PR #910 PR #1051

What I did

  • Organized and led five technical workshops reaching more than 300 participants.
  • Coordinate workshop programming, event logistics, and participant engagement.
  • Built cross-club partnerships and collaborated with organizations including OpenAI and Hugging Face.
Full experience

Experience

Research + Engineering

Internships02Research02Ambassadors02Leadership02
01

Internships

02
Lockheed Martin logo

Machine Learning Intern

Lockheed MartinSummer 2024Tampa, FL

Built and deployed machine-learning systems for aerospace inspection and integrated them into established engineering workflows.

  • Improved the previous CAD/AI comparison model by 80% and reduced inspection time by 25%.
  • Saved 15+ hours and $15,000 weekly through the improved inspection workflow.
  • Maintained less than 5% error across 100+ validation tests and collaborated with 10+ engineers, QA, and operations specialists.
Machine LearningCADValidationProduction data pipelines
SCC Soft Computer logo

MIS Intern

SCC Soft ComputerSummer 2023Largo, FL

Supported network infrastructure and security for healthcare systems serving hospitals and laboratories.

  • Managed 200+ server-port configurations and optimized network pathways.
  • Implemented security measures for 100+ network ports.
  • Reimaged or repaired 50+ systems while maintaining hardware inventory.
NetworkingInfrastructure securitySystems administration
02

Research

02
VARLAB, UCF logo

Undergraduate Researcher

VARLAB, UCFAug 2025 – PresentOrlando, FL

Conducting ML and XR research through virtual environments, experimental systems, and data pipelines.

  • Build Unity-based experimental environments for immersive ML and XR studies.
  • Explore JEPA architectures, vision-language models, and human perception.
  • Support experiment design and data preprocessing for user studies.
UnityXR/VRMachine LearningData pipelines
KSRP, UCF logo

Undergraduate Researcher

KSRP, UCFJan 2026 – Jun 2026Orlando, FL

Completed research on resilient on-device RAG with knowledge graphs for personalized language models.

  • Developed knowledge-graph RAG approaches for resilient personal information storage.
  • Ran local language-model inference with MLC-LLM for edge-device deployment.
  • Evaluated personalization approaches using the LaMP dataset.
GraphRAGMLC-LLMKnowledge graphsEdge AI
03

Ambassadors

02
OpenAI logo

Codex Ambassador

OpenAI2026 – PresentRemote

Supporting the global developer community with practical Codex education, agentic coding workflows, and product feedback.

  • Demonstrate Codex workflows for building, debugging, and shipping software with coding agents.
  • Create developer education that makes agentic coding patterns practical and responsible.
  • Share community feedback that helps improve how developers learn and work with Codex.
CodexAgentic codingDeveloper educationCommunity feedback
Perplexity AI logo

Comet Ambassador

Perplexity AIJan 2026 – Jun 2026UCF

Introduced Perplexity Comet browsing and AI-assisted research workflows to the UCF community during a completed six-month ambassadorship.

  • Demonstrated Comet browsing, search, and research workflows to students.
  • Organized UCF demos and helped students and faculty evaluate AI-assisted web research.
CometAI-assisted researchDemosCommunity outreach
04

Leadership

02
Knight Hacks logo

Director of Workshops & Hackathon Organizer

Knight HacksAug 2025 – PresentOrlando, FL

Leading technical workshops and organizing hackathon programming for the UCF developer community.

  • Organized and led five technical workshops reaching 300+ participants.
  • Built cross-club partnerships and collaborated with external organizations including OpenAI and Hugging Face.
  • Coordinate workshop programming, event logistics, and participant engagement.
AI/ML educationSoftware engineeringEvent operations
AI Club ELHS logo

Project Lead

AI Club ELHS2023 – Jun 2025East Lake High School

Led student machine-learning projects and taught AI fundamentals through June 2025.

  • Led a team of 15+ members building machine-learning applications and research projects.
  • Mentored students in deep learning, computer vision, NLP, reinforcement learning, and robotics.
  • Presented work at school and district events.
PythonComputer VisionNLPReinforcement LearningRobotics

Contact

Let’s Build Something

Open to internships, research, and ambitious collaborations

Have a interesting problem about ML?

I’d love to hear what you’re building and where I can help.

@reach_mrpie
GitHub LinkedIn Résumé

© 2026 Michael Rusu.

Back to top ↑