My research advances the safety, security, and reliability of cyber-physical systems (CPS) by integrating real-time systems, machint learning, and formal methods. I develop algorithms and frameworks that ensure deadline-aware, uncertainty-robust, and provably safe decision-making for autonomous and embedded systems. My work spans early-exit neural architectures, optimizations, safe reinforcement learning, explainable AI, with applications in transportation, robotics, manufacturing and critical infrastructure.