About Me
I'm passionate about advancing brain-computer interfaces to deepen the integration between human cognition and intelligent systems.
Currently pursuing my Master's in Engineering AI at Carnegie Mellon University, with an exchange program at CMU Pittsburgh. I focus on BCIs, agentic AI, and deep learning to build adaptive systems that expand human-AI collaboration.
My research on enhancing neural decoding accuracy using EEGNet for SSVEP-based BCIs was published at the IEEE SIPS 2025 conference in Hong Kong, China.
Beyond research, I'm committed to education and mentorship. As a Teaching Assistant for Introduction to Deep Learning at CMU, I help students build custom PyTorch libraries and train sophisticated models. I also volunteer with Page Turners Kenya, coaching 49 primary school children to enhance their reading skills.
Experience
Designing homework assignments that guide students in building custom PyTorch libraries and training models. Providing comprehensive support through office hours and mentorship.
Investigated engineered nitrogen defects in graphene for enhanced catalytic performance in hydrogen peroxide production. Explored the intersection of materials science and biointerfacing.
Supporting undergraduate students on IoT fundamentals, including sensor integration, Arduino programming, cloud deployment, and real-time monitoring systems.
Developed and implemented user-friendly website designs into functional platforms using React.js and Firebase, including the Avid website interface.
Education
Graduate Studies
Exchange Program
Primary Program
Undergraduate Studies
GPA: 3.57/4.0 • Graduated with Honors
Volunteering
Coaching 49 primary school children to improve their reading comprehension and literacy skills. Developing engaging lesson plans and fostering a love for reading through interactive sessions.
Featured Research
Published at IEEE SIPS 2025
Developed a brain-computer interface using EEGNet to enhance neural decoding accuracy and user interaction through Steady-State Visually Evoked Potentials (SSVEP) techniques. The system enables real-time EEG signal analysis for improved human-computer interaction.