Check out my website!

👀 I'm a senior undergrad pursuing a BS/MS honors in aerospace engineering 🚀 at Georgia Tech. My main interests revolve around applying ML, AI, systems analysis, and data science to topics in aerospace engineering and related industries. That said, I'm always open to exploring a wide range of engineering experiences!

• Coursework: Object-Oriented Programming, Computing for Engineers, Linear Algebra, Dynamics, Thermodynamics & Fluid Fundamentals, Engineering Graphics & Design, Calc 1-3
• Self Learn: Data Structures & Algorithms, C++ Development, Scripting, SQL Essential Training

• Worked on developing comprehensive MBSE analysis of radar backend using MagicDraw, Matlab Radar Toolbox, and Python script
• Designed, SMT soldred, and tested PCB to monitor health and status of radar component

• Worked on developing a novel modeling capability in MATLAB that leveraged orbital physics, parallel computing, and optimization techniques to provide data used in engineering systems analysis trade studies

• Worked on modeling and simulating an underwater rocket launch and habitable lunar platform using MagicDraw, OpenMBEE, version control, and REST API.

• TensorFlow, Scikit-learn (ML)
• OpenCV, Matplotlib (Image Processing)
• Pandas, NumPy (Data Analysis)
• PyBlueZ, Gattlib, Pyyaml (Signal Processing)

• Object Oriented Programming
• Graphics & Game Design

• Web Dev
• NLP
• Node.js Amazon Alexa Skills

• Bash, CMD
• Tangram (ML)

• Linux, Raspbian (Debian Linux)

Key Technologies Used: Python, Python Bluetooth Libraries, Numpy, Pandas, Matplotlib

• Used Python and bluetooth libraries to successfully demonstrate the feasibility of Bluetooth Low Energy for automated proximity-detection for COVID-19 by conducting Raspberry Pi signal experiments

• Used Matplotlib for data visualization and Numpy & Pandas to parse CSV data and run statistical analysis on key signal parameters such as RSSI (Recieved Signal Strength) to design a proximity detection algorithm based on COVID TC4TL (“Too close for too long”) parameters

Key Technologies Used: Python, TensorFlow, Computer Vision, Finite Element Analysis, Dynamic Motion Analysis, 3D CAD

• 3D Printed Physically built CubeSat mockup prototype containing embedded systems and low-light cameras and IMU sensors

• Simulated prototype performance with dynamic motion and finite element analysis (FEA) in Autodesk Inventor

• Used Python and Tensorflow to train ML model on curated dataset and implemented model into debris detection script yielding 95% confidence per detection