With experience spanning product design, robotic systems, nonlinear mechanics, and learning-based methods, my work includes the design and fabrication of physical robotic systems, such as quadruped locomotion platforms and compliant grippers, as well as simulation-driven design using nonlinear finite-element analysis (FEA) for bistable and metamaterial structures. In parallel, I have applied machine learning techniques, including MLPs, CNNs, and reinforcement learning, to model physical behavior, perception tasks, and control-oriented problems. Across both research and industry settings, I emphasize end-to-end engineering—from concept and CAD, through simulation and experimentation, to validation under manufacturing, reliability, and system-level constraints. 

My work draws on a broad technical skillset spanning robotic system design, nonlinear simulation, and learning-based methods. I regularly work with CAD-driven mechanism design, nonlinear finite-element analysis (FEA), and structured experimentation (DOE) to reason about physical behavior, and apply machine learning techniques—including MLPs, CNNs, and reinforcement learning—to model and control physical systems. These skills are grounded in hands-on prototyping and validation across research and product-oriented projects.