AI/ML + Robotics Engineer · ROS2 · Multi-Robot Systems
I build multi-robot systems in ROS2, from simulation to real-world deployment, focusing on reliable systems first and using learning or language guidance only when it clearly adds value.
Ask questions about my background and projects. Use the floating button to open the assistant here, or open it in a separate window if you prefer.
On narrow screens, the launcher opens the assistant in a new window automatically.
AI/ML engineer shipping multi-robot systems in ROS2—simulation, sim-to-real, and language-guided coordination when it genuinely reduces overhead. Ph.D. in Computer Science from UC Irvine (CARL).
Off-hours: hiking, camping, games, and time with my cat.
Three representative threads before the full timeline below.
A ROS2 research platform for human-inspired navigation in multi-agent teams, with PyTorch training and LLM-assisted planning when it improved coordination.
ROS2 · PyTorch · Webots / Gazebo · agentic tooling
View technical backgroundHuman study on whether autonomous navigation support in telepresence lowers cognitive load and improves task efficiency.
Human studies · IEEE ICDL 2024 · robotics UX
IEEE Xplore →Exploring when transformers, memory, and tool-use earn their place in communication-aware multi-robot coordination—not bolted on for novelty.
LLM planning · multi-agent · ongoing CARL work
More detail in Technical background below.
Curated highlights from graduate training and research—not a full résumé. For depth, download the CV or get in touch.
2019–2025
Donald Bren School of Information & Computer Sciences — research in robotics, ML, and multi-agent systems with CARL.
GPA: 3.93/4
2014–2018
Hardware Engineering, Computer Engineering
GPA: 18.24/20
Built a realistic ROS2 platform to study human-inspired navigation in multi-agent systems; integrated human navigation data for training (PyTorch); added Agentic AI (LLM-driven planning, memory, tool-use) enabling language-guided decision-making and multi-robot coordination; prepared distributed training workflows (DDP-ready); ran Webots/Gazebo simulations with visual/sequence models. Manuscript under review; poster/papers at SAB 2024 and IEEE ICDL 2024.
IEEE ICDL 2024
Human study on whether autonomous navigation aids in telepresence reduce cognitive load and improve efficiency. IEEE ICDL 2024.
Implemented an 8-bit spiking neural network for embedded targets and designed an 8-bit quantization technique that reduced power by 12%–18% on MNIST/CIFAR10/20 with only 3%–7% accuracy drop.
Peer-reviewed and conference work from my graduate research. Below are two representative highlights; the full list and citation graph live on my public profiles.
Open to AI/ML and robotics roles where systems thinking matters. Email is best—include role, timing, and how you found me.
Ph.D. CS, UC Irvine · CARL · Google Scholar
South San Francisco, CA
CV available for download from the About section.