具身世界模型推理INFRA工程师 - XiaomiRobotics
Tasks
- Accelerate embodied world model inference
- Adapt CFG parallelism
- Adapt multi token prediction for inference
- Collaborate with algorithm team to optimize inference speed for production and open source models
- Implement FP8 quantization
- Implement NVF4 quantization
- Optimize expert parallelism for inference framework
- Optimize tensor parallelism for inference framework
- Support multimodal model and video model inference acceleration and commercialization
Perks/Benefits
- N/A
Skills/Tech-stack
CFG Parallelism | Diffusion Models | Expert parallelism | FP8 Quantization | Multi Token Prediction | Multimodal AI | NVF4 Quantization | Quantization | Tensor Parallelism
Education
Roles
Related jobs
-
机器人VLA算法研究员 - XiaomiRobotics CNY 500K-500KDeep learning | Diffusion Models | Language Models | Machine Learning | Mixture of ExpertsEntry-level Full Time北京7h ago
-
Mid-level Full Time上海1d ago
-
C++ | CUDA | Data parallelism | DeepSpeed | InfinibandEntry-level Full TimeChina5d ago
-
3D Gaussian Splatting | Gaussian Splatting | Multimodal AI | Nerf | ROS2Entry-level Full TimeChina5d ago
-
C++ | Edge Deployment | GPU | Hardware compilation | Language ModelsMid-level Full TimeChina5d ago
-
Senior-level Full TimeBeijing Yizhuang, China7d ago
-
具身智能算法实习生 (Manipulation) CNY 25K-37KCLIP | Code debugging | Data Preprocessing | Deep learning | Diffusion ModelsEntry-level Internship深圳8d ago
-
Entry-level Internship上海8d ago
-
AI Software Engineer Intern CNY 38K-50KAgent Development | Computer Vision | Deep learning | Fine Tuning | Inference OptimizationCareer development opportunities | Collaborative environment | On site work experienceEntry-level Full Time InternshipCHN - Minhang, China9d ago
-
Machine Learning Engineer (Training Optimization) CNY 240K-480KCUDA | Data Types | DeepSpeed | Diffusion Models | Distributed TrainingSenior-level Full TimeBeijing, Beijing, China13d ago
-
Senior-level Full Time上海16d ago
-
None Full Time深圳、北京、上海19d ago
-
Entry-level Full Time深圳、北京、上海19d ago
-
AI Engineer (Biometrics and Data Science) CNY 272K-370KA/B | A/B Testing | Auto Testing | B testing | CI/CDMid-level Full TimeShanghai Jing'An Office, China21d ago
-
C++ | CPU architecture | Deep learning | Fine Tuning | GPU ComputingOn-site workEntry-level Full TimeCHN - Minhang, China24d ago
-
Agentic Inference | CUDA | Distributed Training | Docker | GPU ComputingSenior-level Full TimeChina, Beijing26d ago
-
Mid-level Full Time深圳28d ago
-
多模态大模型算法工程师(Vlm / 自动驾驶方向) CNY 180K-264KAgent modeling | Autonomous Driving | Autoregressive modeling | BEV | Behavior ModelingEntry-level Full Time北京、苏州28d ago
-
Entry-level Full Time北京、深圳、上海1mo ago
-
Senior Software Engineer, 3D/4D Reconstruction CNY 417K-540K3D Computer Vision | Autonomous Driving | Computer Vision | Deep learning | Dense ReconstructionSenior-level Full TimeChina, Beijing1mo ago
-
Computer Vision | CoreML | Deep learning | Diffusion Models | GLSLSenior-level Full TimeBeijing, China1mo ago
-
Ai工程师 CNY 180K-300KAI infrastructure | AIGC | Automation | Deep learning | Language ModelsCollaborative culture | Growth opportunities | Latest hardware access | Technical community impactMid-level Full TimeShenzhen1mo ago