具身世界模型推理INFRA工程师 - XiaomiRobotics
北京
CNY 240K-480K (estimate) Senior-level Full Time
Tasks
- Accelerate embodied model inference
- Adapt multi token prediction for inference
- Collaborate with algorithm teams to improve inference speed
- Implement CFG parallelism adaptation
- Optimize expert parallelism for inference framework
- Optimize tensor parallelism for inference framework
- Quantize models using FP8
- Quantize models using NVF4
- Support model deployment and open source release
Perks/Benefits
- N/A
Skills/Tech-stack
CFG Parallelism | Diffusion Models | Expert parallelism | FP8 | Multi Token Prediction | Multimodal AI | NVF4 | Tensor Parallelism
Education
Language: zh
Views:
3
Clicks:
1
Saves: 0
Related jobs
-
Computer Graphics | Computer Vision | CoreML | Deep learning | Diffusion ModelsSenior-level Full TimeBeijing, Beijing, China23h ago
-
AWQ | AWS | Batching | CPU architecture | CUDASenior-level Full TimeGuangzhou, Guangdong, China6d ago
-
具身智能 / Vla / Wam 算法工程师 CNY 180K-360KC plus plus | Camera Calibration | Coordinate transformations | Data Quality | Data labelingEntry-level Full Time上海7d ago
-
具身智能-强化学习(灵巧操作方向) 实习生 CNY 25K-37KActor-critic | Diffusion Models | Distributed Training | Embodied intelligence | Flow matchingEntry-level Full Time Internship深圳9d ago
-
Mid-level Full Time上海9d ago
-
Mid-level Full Time杭州10d ago
-
机器人VLA算法研究员 - XiaomiRobotics CNY 500K-500KAction Generation | Data Engineering | Deep learning | Diffusion Models | Machine LearningEntry-level Full Time北京12d ago
-
Mid-level Full Time北京 R12d ago
-
具身世界模型推理INFRA工程师 - XiaomiRobotics CNY 240K-480KCFG Parallelism | Diffusion Models | Expert parallelism | FP8 | Machine LearningSenior-level Full Time北京12d ago
-
3D Gaussian Splatting | 3D Geometry | 3D Object Detection | Algorithms | Autoregressive GenerationMid-level Full Time北京、上海、苏州13d ago
-
Behavior Cloning | C++ | Cloud processing | Computer Vision | ControlEntry-level Internship北京、上海 R16d ago
-
Mid-level Full TimeShenzhen, Guangdong, China18d ago
-
具身智能算法实习生 (Manipulation) CNY 25K-37KCLIP | Computer Vision | Deep learning | Diffusion Models | Fine TuningEntry-level Internship深圳21d ago
-
Entry-level Internship深圳21d ago
-
AWQ | AWS | Accelerate | Azure | BatchingMid-level Full TimeShenzhen, Guangdong, China R22d ago
-
Generative AI - ML System Engineering CNY 360K-600KC++ | CUDA | Compilation | Data pipeline | Diffusion ModelsFully remote option | On-site work flexibilitySenior-level Full TimeShanghai R27d ago
-
Entry-level Full Time深圳、上海1mo ago
-
多模态大模型算法工程师（Vlm / 自动驾驶方向） CNY 180K-264KAgent systems | Autonomous Driving | BEV | Behavior Modeling | C++Entry-level Full Time北京、苏州1mo ago
-
【26届校招】基础模型与多模态大模型算法工程师 CNY 216K-360KBERT | BLIP | C++ | CLIP | Data pipelineCareer growth path | Compute resources | Innovation freedom | Research resources | Training programEntry-level Full Time深圳1mo ago
-
Entry-level Full Time深圳、上海1mo ago
-
AI Software Engineer Intern CNY 38K-50KCUDA | Distributed Systems | FP8 | FasterTransformer | Flash AttentionOn-site workEntry-level Full Time InternshipCHN - Minhang, China1mo ago
-
AI Software Engineer Intern CNY 38K-50KCUDA | Compiler optimization | Continuous batching | Distributed Systems | Dynamic batchingOn-site workEntry-level Full Time InternshipCHN - Minhang, China1mo ago
-
C++ | CUDA | Data parallelism | DeepSpeed | InfinibandEntry-level Full TimeChina1mo ago
-
3D Gaussian Splatting | Gaussian Splatting | Multimodal AI | Nerf | ROS2Entry-level Full TimeChina1mo ago
-
Senior-level Full TimeBeijing Yizhuang, China1mo ago