Resume

• Coursework: Embedded Systems, Biomedical Instrumentation, Real-Time Digital Signal Processing, Circuits, Systems & Signals, Numerical Methods, Statistics, Differential Equations & Linear Algebra, Intro to Computational Engineering Design

• Applying machine learning to study gut–brain interactions.

• Directed a team of student engineers to optimize neural networks for deployment on embedded systems (Raspberry Pi series).
• Designing a reusable quantization pipeline using ExecuTorch and an inference backend to support keyword spotting and future neuroprosthetic control applications.
• Quantized an EMG gesture MLP to INT8 with ONNX Runtime (311 KB), running at 0.43 ms per sample on a Raspberry Pi Zero 2 W against 1.04 ms for FP32, at a 0.13-point accuracy cost.

Project page

• Built a capsule network for EEG motor-imagery classification (BCI Competition IV-2a) toward prosthetic arm control, reordering channels to match scalp topography.
• Used Captum attribution to inspect what the EEG classifiers were keying on.

• Contributed a 3D feature visualization view to phy, an open-source spike-sorting package for neuroscience, designing the projection pipeline and camera controls for inspecting neural spike data.

Project page

• Developed a real-time Laser Speckle UI in Python, using Basler cameras and Arduinos for automated laser intensity control.
• Enhanced speckle pattern evaluation by implementing contrast analysis algorithms to maximize measurement precision.
• Refactored contrast adjustment scripts from MATLAB to Python, enabling integration with the real-time Laser Speckle Analysis UI.

Project page