该职位负责开发和部署新一代 3D Gaussian Splatting、神经渲染和生成式 AI 技术,用于自动驾驶场景重建、仿真和闭环评估。职责包括构建端到端研发流程、设计重建算法、制作可编辑的 3D 资产、将输出集成到仿真和感知系统中,以及优化训练、渲染和推理。该职位要求相关领域硕士或更高学历,熟悉深度学习和图形学工具,并具备至少一年相关研发经验。
Master’s degree or higher in computer science, artificial intelligence, electronic information, automation, surveying and mapping, robotics, or a related field
Required Previous Experiences
At least one year of relevant R&D experience in 3D Gaussian Splatting, NeRF, neural rendering, 3D reconstruction, SLAM, SfM, or MVS
Preferred Qualifications
Experience with autonomous-driving scene data processing pipelines and multi-sensor data including cameras, LiDAR, IMU, and GNSS
Familiarity with 3DGS, Street Gaussian, PVG, EmerNeRF, UniSim, DriveDreamer, Cosmos, and World Model
Experience with autonomous-driving simulation projects, closed-loop simulation, SIL/HIL, Unreal Engine, Omniverse, and Isaac Sim
Experience in road-scene, city-scale, and dynamic-scene reconstruction and producing editable simulation assets
Familiarity with CUDA acceleration, real-time rendering, distributed training, and model compression or inference optimization
Open-source project participation or conference publications in computer vision, robotics, or related fields
Experience in autonomous-driving perception, BEV, occupancy, 4D labeling, data closed loops, and corner-case generation