Kazim Mohammed Abbas

Designed and built a standalone voice-based software assistant from scratch. Created a real-time audio system that allows fast, natural conversations where users can speak and interrupt at any time. Built the full system end to end, including audio input, session handling, and event coordination, and improved performance and stability through repeated testing. This allowed the user to input their goals for the day and the agent could refer and corroborate with other participants to make an ultimate accountability app.

Supported community fundraisers for three years, assisting with setup and event operations. In the final year, served as an assistant organizer for a large-scale community fundraiser and theatrical event that raised over $100,000 for humanitarian assistance and social services. Helped coordinate event logistics, setup, and on-site operations, including preparing the venue, organizing food and décor, and supporting a live theatrical performance to enhance community engagement.

Participated in one of the largest hackathons in the United States, Carnegie Mellon University's NexHacks, working on an AI-based surveillance and situational awareness project using real-time computer vision. Helped build the frontend interface to display detected events and system outputs in a clear and organized way. Contributed to an agent-based workflow that routed detected signals to different response paths based on context. Tested system behavior, adjusted parameters, and documented limitations such as false positives, edge cases, and performance tradeoffs.

Participated in Google DevFest, working on a computer vision prototype that simulated automated defect detection for infrastructure inspection. Built a Python application that processed image inputs, highlighted potential defects, and displayed confidence scores using a simple visual interface. Integrated an AI-based analysis step to evaluate detected defects and trigger alerts when issues exceeded a threshold. Focused on making system outputs easy to interpret, testing edge cases, and reasoning about false positives, reliability, and alerting logic.

Built a computer-vision–based adaptive traffic signal system using Python and OpenCV. Designed logic to detect vehicles from live video, compute rolling traffic demand, and dynamically adjust signal timing in real time. Implemented a state machine for green/yellow/red phases, integrated hardware light controls, and modeled fuel and CO₂ impact from reduced idle time. Focused on reliability, noise reduction, and real-time decisionmaking under uncertainty.