NVIDIA has continuously reinvented itself over the past three decades. Our invention of the GPU fueled the growth of PC gaming, redefined modern computer graphics, and revolutionized parallel computing. More recently, GPU-accelerated deep learning ignited modern AI, enabling computers, robots, and autonomous vehicles to perceive and understand the world. This is our life’s work: amplifying human imagination and intelligence.
We are seeking a Senior Parking Perception Fusion Engineer in Shanghai or Beijing to develop, evaluate, and adapt production Parking solutions across OEM partners, vehicle platforms, and regions. The role covers driving and parking applications, including multimodal sensor fusion, object tracking, perception post-processing, system evaluation, and vehicle adaptation. You will work across algorithms, production software, vehicle systems, and large-scale evaluation to help deliver and scale NVIDIA autonomous-driving solutions globally.
What You’ll Be Doing:
Develop and optimize perception-fusion and post-processing algorithms for parking applications.
Evaluate perception performance across OEM carlines, platforms, regions, ODDs, and sensor configurations, ensuring that offline KPIs reflect real-world performance.
Triage complex perception issues, identify root causes, and drive end-to-end resolution across algorithms, software, sensors, and vehicle integration.
Build production fusion and post-processing solutions for parking-space understanding, curb and obstacle processing, object suppression and recovery, ultrasonic-sensor fusion, and vehicle adaptation.
Develop AI-assisted tools for large-scale replay, KPI evaluation, issue classification, root-cause analysis, and regression detection.
Drive parking bring-up for new carlines, from sensor integration and KPI validation to on-road debugging, certification readiness, and production delivery.
What We Need to See:
MS, PhD, or equivalent experience in Computer Science, Computer Engineering, Robotics, Mathematics, Physics, or a related field, with 3+ years of relevant industry experience.
Strong foundations in image processing, 3D multi-view geometry, nonlinear optimization, linear algebra, probability, and uncertainty modeling.
Solid knowledge of sensor fusion and state estimation, including KF/EKF, Bayesian estimation, data association, and multi-object tracking.
Strong C/C++ and Linux skills, including modern C++, algorithms, data structures, debugging, software design, and performance optimization.
Hands-on deep-learning experience in perception or robotics, with strong Python skills for prototyping, evaluation, data analysis, and automation.
Proven ability to diagnose system-level issues and collaborate effectively across teams, regions, cultures, and time zones.
Ways to Stand Out from the Crowd:
Experience delivering production perception-fusion or post-processing systems for parking, active safety, ADAS, autonomous driving, or robotics.
Experience with cameras, lidar, radar, ultrasonic sensors, IMU, GNSS, and vehicle odometry in multimodal fusion systems.
Hands-on experience with parking-space detection, curb and obstacle processing, near-field occupancy, ultrasonic-sensor fusion, or parking perception post-processing.
Experience taking algorithms from prototype through vehicle integration, large-scale evaluation, on-road debugging, certification, or production deployment.