I am a robotics software engineer in the San Francisco Bay Area, currently on Zoox's core AI team building intelligent driving features that make our vehicles autonomous, including high-speed highway behavior and decision systems. I also develop LLM systems that triage fleet issues and escalate them to AI teams, helping scale fleet autonomy as we expand into new metropolitan areas. My work spans motion planning, controls, machine learning, and systems engineering, with contributions recognized through patents and peer-reviewed publications.
I focus on shipping autonomy behavior that can survive the messy edge cases outside a lab: high-speed driving dynamics, uncertainty, multi-agent interaction, decision model quality, and reliable evaluation loops.
Developing and testing intelligent driving features that advance autonomous mobility, with emphasis on highway behavior, decision systems, and system-level performance. I also build LLM workflows that triage fleet issues, escalate them to AI teams, and support reliable operations as the fleet expands into new metropolitan areas.
At Drive System Design, built data-driven methodologies to improve engineering analysis across mechanical, hydraulic, and control systems.
Implemented local learning methods to approximate nonlinear robot dynamics and improve model-based control for a seven-degree-of-freedom robot.
Research on uncertainty-aware planning for multi-agent systems, with an emphasis on dynamic obstacles, minimum sensing, and practical navigation.
Explore the Multi-agent CC-RRT projectDeveloped self-calibration and closed-loop seeking methods for hidden-target localization using range-bearing packets from relays with unknown position and yaw.
Explore the adaptive localization projectExplored sampling-based planning and coordinated mapping strategies for autonomous agents operating in uncertain environments.
A record of original technical contributions in autonomous vehicles, motion planning, and applied machine learning which spans granted patents, conference publications, and competitive fellowships.
Core AI team building intelligent driving features and trajectory generation for autonomous mobility, alongside LLM fleet triage to scale operations across metropolitan areas.
Autonomous vehicle engineering on production mobility systems.
Machine learning for hydraulic correlation, model quality, and gearbox prognostics.
Robotics, controls, machine learning, and multi-agent motion planning.
Rigorous training in optics, statistical and quantum mechanics, electrodynamics, and classical mechanics.
For focused conversations, technical advising, collaboration, or career discussions, you can schedule a 1-on-1 directly or reach out through the channels linked here.