具身世界模型推理INFRA工程师 - XiaomiRobotics
Tasks
- Adapt multi token prediction for inference
- Apply FP8 quantization for models
- Apply NVF4 quantization for models
- Collaborate with algorithm team to optimize production rollout and open source release
- Implement tensor parallelism and expert parallelism for inference framework
- Integrate CFG parallelism for inference
- Optimize inference throughput for embodied world models
Perks/Benefits
- N/A
Skills/Tech-stack
CFG Parallelism | Diffusion Models | Expert parallelism | FP8 | Model Quantization | Multi Token Prediction | Multimodal AI | NVF4 | Tensor Parallelism | Video models
Education
Related jobs
-
机器人VLA算法研究员 - XiaomiRobotics CNY 500K-500KAction Generation | Data Modeling | Deep learning | Diffusion Models | Machine LearningMid-level Full Time北京4h ago
-
Mid-level Full Time北京4h ago
-
Senior-level Full Time上海、北京5h ago
-
【27届校招】嵌入式camera系统培训生 CNY 25K-37KC# | C++ | Color Space Conversion | Color correction | Color spaceEntry-level Full Time广州1d ago
-
【27届校招】AI Infra工程师(深度学习优化方向) CNY 180K-300KKnowledge Distillation | Model Pruning | Model Quantization | Model Sparsity | ONNXNone Full Time广州、北京、上海1d ago
-
Entry-level Full Time深圳、上海、广州1d ago
-
None Full Time武汉1d ago
-
None Full Time上海1d ago
-
Principal Machine Learning Engineer CNY 144K-240KApache Arrow | Apache Spark | DPO | Deep learning | DeepSpeedSenior-level Full TimeChina R1d ago
-
Mid-level Full Time惠州 R6d ago
-
Mid-level Full Time深圳、上海、杭州7d ago
-
AWQ | AWS | Accelerate | Azure | BatchingSenior-level Full TimeGuangzhou, Guangdong, China R7d ago
-
C# | C++ | Fine Tuning | GPU Acceleration | InferenceCareer development | Mentorship guidance | Onsite collaborationMid-level Full TimeCHN - Minhang, China7d ago
-
Entry-level Internship上海8d ago
-
Mid-level Full Time上海8d ago
-
3D视觉算法工程师 CNY 180K-300K3D Pose Estimation | 3D Reconstruction | 6D Pose | 6D Pose Estimation | Audio ProcessingMid-level Full Time深圳8d ago
-
Senior-level Full Time上海 R8d ago
-
Senior-level Full Time上海 R8d ago
-
Mid-level Full Time北京、上海8d ago
-
Mid-level Full Time上海8d ago
-
Entry-level Internship Part TimeWuxi, Jiangsu, China8d ago
-
Mid-level Full TimeGuangzhou (DTC), China R8d ago
-
Action Model | Action Transformer | Autonomous Navigation | Computer Vision | Embedded SoftwareMid-level Full TimeBeijing, China9d ago
-
Robot learning-Manipulation AI Senior算法工程师 CNY 144K-240KComputer Vision | Diffusion Models | Distributed Training | GPU Computing | Generative ModelsSenior-level Full Time深圳9d ago
-
Robot learning-Generative AI 算法工程师 CNY 216K-360KComputer Vision | Diffusion Models | Embodied AI | Flow-based models | Foundation ModelsMid-level Full Time深圳、苏州、北京、杭州9d ago