Hello, I’m Burak Tufekci, a hardware/software engineer/researcher in machine learning, security, and RTL design. I recently completed my PhD in Computer Science and Engineering at the University of North Texas, where my research focuses on identifying vulnerabilities and enhancing the security of drones through machine learning-based Intrusion Detection Systems.

My career began at SemiMobility, where I worked as a Digital (RTL) Design Engineer on designing control systems for high-frequency 3-phase machine drives. At SemiMobility, I worked on a project aimed at controlling 3-phase machine drives and innovating switch technology for high-frequency operations. The core challenge was to improve the performance of power switches, traditionally based on MOSFET technology and operating at 50-60 kHz. Our objective was to increase this frequency to 200 kHz using newer switch designs based on germanium and silicium oxide, which allowed for higher frequencies with minimal energy loss. I designed and tested the following modules: Clarke, Park, CORDIC, PI Controller/Scheduler, PWM, SVM, Encoder Interface, and ADC.

Following my work at SemiMobility, I joined Baykar to lead a team in developing an autonomous take-off and landing system for drones. The goal was to eliminate dependency on satellite data by using radar-based distance calculations for positioning the drone during landing and take-off. I designed and implemented a radar-based system capable of locating drones with ±1 meter accuracy, successfully delivering a working prototype in just six months—well ahead of the project’s nine-month deadline. This involved developing real-time algorithms to process radar signals, which enabled precise distance measurements that allowed for highly accurate drone positioning without relying on GPS. By managing and being part of a cross-functional team, I have experienced collaboration between software, hardware, and testing teams to deliver a robust, scalable solution that meets all technical and time-related requirements. 

During my PhD, I primarily focused on securing drone systems from cyber threats using machine learning-based IDS. I’ve explored various approaches to strengthen the operational security of drones through the use of RNN-LSTM models and supervised ML architectures. These research efforts have resulted in the publication of multiple papers on drone and IoT security that advance the understanding of how to mitigate cyber risks in emerging autonomous systems. 

Through my career and research, I have always aimed to push the boundaries of innovation, whether it's optimizing hardware design or developing AI-driven security solutions. I am passionate about exploring the intersections of machine learning, RTL design, and security, and I look forward to continuing to contribute to these fields.