该职位负责开发和实现用于自动驾驶场景重建、仿真资产制作、动态物体建模和闭环评估的 3D Gaussian Splatting 与神经渲染算法。职责包括构建重建和渲染流水线、优化训练与推理、将成果集成到仿真和感知系统中,并与数据生产和算法团队协作。该职位要求相关专业硕士学位、深度学习和图形学开发技能,以及 3D 重建或相关领域的研发经验。
Master's degree or above in Computer Science, Artificial Intelligence, Electronic Information, Automation, Surveying and Mapping, Robotics, or a related field
Required Previous Experiences
R&D experience in 3D Gaussian Splatting, NeRF, Neural Rendering, 3D Reconstruction, SLAM, SfM, or MVS
Engineering implementation experience converting algorithm prototypes into stable, scalable production pipelines
Preferred Qualifications
Familiarity with 3DGS, Street Gaussian, PVG, EmerNeRF, UniSim, DriveDreamer, Cosmos, and World Model
Project experience in autonomous-driving simulation, LogSim, WorldSim, closed-loop simulation, SIL/HIL, Unreal Engine, Omniverse, or Isaac Sim
Experience in road-scene reconstruction, city-scale reconstruction, dynamic-scene reconstruction, or production of editable simulation assets
Familiarity with CUDA acceleration, real-time rendering, distributed training, model compression, and inference optimization
Participation in open-source projects or papers published at CVPR, ICCV, ECCV, NeurIPS, ICLR, ICRA, IROS, or SIGGRAPH
Experience in autonomous-driving perception, BEV, Occupancy, 4D Label, data loops, or corner-case generation