Senior Software Engineer, Context Fusion and Multi-Vehicle Adaptation - Autonomous Vehicles
Nvidia1 day ago
Shanghai, China or Beijing, ChinaSenior
Responsibilities
- Analyze, triage, and resolve complex Context Fusion issues across NDAS programs and carlines using replay tools, log-based diagnostics, and on-vehicle debugging.
- Develop and improve fusion logic integrating perception outputs, map signals, and vehicle state into driving-relevant environment representations.
- Adapt and tune Context Fusion modules across vehicle platforms, sensor configurations, map providers, and regional driving environments.
- Conduct on-vehicle validation, issue reproduction, debugging, and performance tuning.
- Design testing tools, automation pipelines, and quality metrics for triage, cross-carline comparison, and engineering productivity.
- Evaluate fusion outputs and their effects on planning, prediction, and active safety, and propose production solutions.
- Travel domestically and internationally for on-site vehicle testing and OEM collaboration as needed.
Requirements
- BS/MS, or equivalent experience, in Computer Science, Computer Engineering, Robotics, Electrical Engineering, Mathematics, Physics, or a related discipline.
- More than 3 years of relevant industry experience in autonomous driving, robotics, perception, mapping, localization, sensor fusion, planning, active safety, or real-time embedded systems.
- Strong system-level debugging experience using logs, replays, metrics, visualization tools, or vehicle testing.
- Strong C/C++ programming skills and a background in 3D geometry, coordinate systems, state estimation, probabilistic modeling, numerical optimization, and real-time fusion systems.
- Experience with production programs, vehicle integration, parameter tuning, validation, or release readiness across multiple platforms, carlines, or customers.
- Clear technical communication in English and the ability to collaborate with global teams, OEM partners, and cross-functional stakeholders.
- Preferred experience includes map-perception fusion, HD/SD maps, online mapping, road topology, lane-level context, traffic signs/lights, mapless or map-degraded driving, BEV world models, occupancy grids, occlusion reasoning, static obstacle modeling, free-space estimation, scenario understanding, Kalman filters, particle filters, factor graphs, multi-object tracking, SLAM, localization, or map matching systems.
Benefits
- Based in Beijing or Shanghai.
- Domestic and international travel for on-site vehicle testing and OEM collaboration may be required.
Tech Stack
CC++
Categories
Robotics
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.