Haixi Zhang

Hi, I’m Haixi Zhang, an ML / Computer Vision / Robotics Engineer based in San Jose, CA. I hold an M.Eng. in Electrical & Computer Engineering from Cornell University and a B.S. in Electrical & Computer Engineering from the University of Rochester.

I specialize in production perception systems that combine multimodal sensor data, 3D geometry, deep learning, and accelerated onboard inference. At Tensor Auto, I have independently developed three company-level ML/CV systems, including two neural calibration systems deployed in production and an active occupant-state perception system.

FEATURED INDUSTRY WORK Production Perception Systems—Built from Data to Deployment End-to-end ownership across sensor data engineering, geometric formulation, distributed training, evaluation, TensorRT optimization, and onboard C++ integration. 3 independently owned systems 2 production deployments 500+ GB multimodal sensor data 10° → <1° calibration recovery LCCNet · Deployed LiLiNet · Deployed OMS · Active Development Explore selected work →

Technical Focus

Multimodal Perception & Geometry

Building learning systems around physical sensor relationships, including camera–LiDAR calibration, cross-LiDAR alignment, occupant perception, and SE(3) / SO(3) geometry.

Production ML Engineering

Taking models from PyTorch and distributed training through ONNX / TensorRT optimization, performance profiling, and integration into production C++ systems.

Data & Evaluation Systems

Developing fleet-scale sensor pipelines, automatic labeling, session-isolated evaluation, hard-case analysis, and regression testing for defensible deployment decisions.

I enjoy working across the full perception lifecycle—from data and modeling to runtime integration and benchmarking—and collaborating with cross-functional teams to improve end-to-end system quality.

Outside engineering, I’m fascinated by world history from the Renaissance through the Second Industrial Revolution, and I remain an enthusiastic fan of Yes, Prime Minister.

Interested in production perception, autonomous systems, or applied computer vision? I’d love to connect.