Vaughn Campos

A closed-loop satellite attitude determination and control system: EKF attitude estimation, PID/LQR/cascaded control, autonomous fault detection, and real single-satellite orbital dynamics, flown against a hardware-abstracted flight-software boundary.

Real-time video streaming iOS app and web platform, built end-to-end as a full stack engineer at SmallTalk, the studio behind JellyJelly.

AI-powered healthcare workflow platform for generating insurance appeals.

A general-purpose C++ rigid-body physics engine — constraints, actuators, sensors, and a double-precision orbital-mechanics module — for writing real controls/flight software against a simulated vehicle.

A simulation framework for optimizing satellite constellation parameters.

An ESP32 + SimpleFOC reaction-wheel robot that balances on one edge through pure momentum exchange, no ground contact.

A from-scratch C++/OpenGL 2D+3D rendering engine, a faster, more customizable alternative to pygame, with batched primitive rendering, GPU scalar-field visualization, and a configurable lighting model.

An LSTM model for forecasting New York City electricity demand, built during a summer internship at Orenda Power to support day-ahead and real-time wholesale market trading decisions.

A student research team building a pair of 3U CubeSats for lunar orbit under NASA's CubeQuest Challenge. I trained a CNN to detect the Sun, Earth, and Moon for optical attitude determination.

An AI calendar assistant that reads and edits your Google Calendar through natural language, with tool-calling support for flight search, email drafting, and weather-aware packing lists.

A CLI tool that downloads NOAA's HRRR weather forecast data and stores the variables that actually drive electricity demand in a queryable local database.