数据生成算法工程师
上海、北京
社招
全职
数字技术
本科及以上
3-5 年
职位描述
负责视频世界模型（World Model）研发，包括数据构建、预训练、后训练与评测体系建设。 研究并实现 Diffusion、Flow Matching、AR Transformer、Video VAE 等生成模型。 构建可控场景生成能力，实现天气、光照、交通参与者行为、Ego轨迹等因素编辑与生成。 探索 World Model 在智能辅助驾驶仿真、闭环评测、数据生成、VLA/WAM 等方向的应用。 负责大规模视频训练与推理优化，包括分布式训练、模型压缩和推理加速。 跟踪学术前沿，复现并改进相关工作，如 Sora、Cosmos、Genie 2、OmniDreams 等。
职位要求
任职要求 计算机、自动化、人工智能等相关专业硕士及以上学历。 扎实掌握深度学习基础，熟悉 Transformer、Attention、VAE、Diffusion、Flow Matching 等模型。 熟练使用 Python、PyTorch、CUDA，具备大规模训练经验。 熟悉视频生成、多模态大模型、智能辅助驾驶感知预测规划中的至少一个方向。 熟悉 Megatron、DeepSpeed、FSDP、TensorRT 等训练部署框架者优先。 具有顶会论文或开源项目经验者优先。 加分项 具备视频生成模型训练经验（Sora、Wan、Cosmos、Seedance 等技术路线）。 具备智能辅助驾驶数据闭环、仿真系统或 VLA/WAM 研发经验。 熟悉 DMD、Consistency Model、Rectified Flow、Self-Forcing 等生成模型加速技术。 有千万级视频数据处理和集群训练经验。
投递
NIO is a pioneer and a leading company in the premium smart electric vehicle market. Founded in November 2014, NIO’s mission is to shape a sustainable and brighter future together. NIO aims to build a community starting with smart electric vehicles to share joy and grow together with users.
NIO designs, develops, jointly manufactures and sells premium smart electric vehicles, driving innovations in next-generation technologies in autonomous driving, digital technologies, electric powertrains and batteries. NIO differentiates itself through its continuous technological breakthroughs and innovations, such as its industry-leading battery swapping technologies, Battery as a Service, or BaaS, as well as its proprietary autonomous driving technologies and Autonomous Driving as a Service, or ADaaS.
NIO’s models for sale include the all-new smart electric flagship SUV ES8, the smart electric flagship coupe SUV EC7, the smart electric mid-large SUV ES7, the smart electric flagship sedan ET7, the all-new smart electric all-round SUV ES6, the all-new smart electric coupe SUV EC6, the smart electric mid-sized sedan ET5, and the smart electric tourer ET5T.
