Summary
Luke Roberto is a Machine Learning Engineer with nine years of experience building self-learning systems that bridge optimal control, deep reinforcement learning, and practical production needs. He led ML efforts at Cadence—architecting a 100k+ PCB dataset pipeline and a distributed neural-network-accelerated MCTS for layout and routing—and now applies that expertise to industrial ML challenges at Gecko Robotics. His background spans autonomy and perception (Skydio, Zenuity), robotics research at MIT and Northeastern, and hands-on systems work from LADAR modeling to SLAM, giving him a rare blend of control theory, planning, and data-driven learning. He’s recognized for technical leadership and research impact (eCTC Best Paper, Cadence Rising Star) and has co-advised multiple MIT master’s theses, reflecting a commitment to mentoring and rigorous methods. Notably, he combines optimal-control instincts with scalable data engineering—building both the algorithms and the pipelines needed to make them learn continually in complex, real-world domains.
9 years of coding experience
8 years of employment as a software developer
Bachelor’s Degree Mechanical Engineering w/ Concentration in Robotics Instrumentation and Control, Bachelor’s Degree Mechanical Engineering w/ Concentration in Robotics Instrumentation and Control at Massachusetts Institute of Technology
Master of Science - MS Computer Science, Master of Science - MS Computer Science at Northeastern University
English, Spanish