具身世界模型推理INFRA工程师 - XiaomiRobotics
Tasks
- Accelerate embodied world model inference
- Adapt multi token prediction for inference
- Enable CFG parallel adaptation
- Implement tensor parallel and expert parallel in inference framework
- Optimize inference throughput with algorithm team
- Quantize models using FP8
- Quantize models using NVF4
- Support deployment and open sourcing of optimized models
Perks/Benefits
- N/A
Skills/Tech-stack
CFG Parallelization | Diffusion Models | Expert parallelism | FP8 Quantization | Inference Optimization | Multi Token Prediction | Multimodal Models | NVF4 Quantization | Tensor Parallelism | Video models
Education
Related jobs
-
Entry-level Full Time北京、上海11h ago
-
AGI 服务端资深工程师-Talkie&星野 CNY 180K-300KData Engineering | Dify | Distributed Systems | Go | Inference OptimizationMid-level Full Time北京、上海11h ago
-
Entry-level Full Time深圳、上海7d ago
-
【26届校招】大语言模型后训练算法工程师(Foundation Model) CNY 240K-480KData loading | Distributed Training | Docker | Fine Tuning | Inference OptimizationEntry-level Full Time上海、深圳7d ago
-
Agent 服务端开发实习生(AI Agent / AI App) CNY 37K-37KContainerization | Cpluspluplus | Dify | Distributed Systems | GoEntry-level Internship北京、上海7d ago
-
AGI 服务端资深工程师 (AI Agent / AI App) CNY 180K-300KBackend Development | Benchmarking | Data Engineering | Dify | Distributed SystemsMid-level Full Time北京、上海7d ago
-
AGI 服务端工程师 (AI Agent / AI App) CNY 180K-300KBenchmarking | C++ | Containers | Data Engineering | DifyMid-level Full Time北京、上海7d ago
-
AGI 研发 Leader(AI Agent / AI App) CNY 240K-480KDify | Inference Optimization | LLM post training | Langchain | Language ModelsSenior-level Full Time北京、上海7d ago
-
Entry-level Full Time北京、上海7d ago
-
Senior AI Software Engineer CNY 240K-480KAPI Integration | Autogen | Chain-of-Thought | CrewAI | LLM APIsGlobal team collaboration | Growth opportunities | Inclusive work environmentSenior-level Full TimeChengdu, China8d ago
-
Senior-level Full Time上海、武汉、北京9d ago
-
Senior-level Full Time上海9d ago
-
Mid-level Full Time上海9d 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9d 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13d ago
-
Entry-level Full Time深圳、上海13d ago
-
【26届校招】Research Scientist (VLM 架构研发) CNY 500K-500KASIC | Attention | Cross-modal fusion | GPU | Inference OptimizationEntry-level Full Time上海、深圳、北京13d ago
-
Mid-level Full Time北京17d ago
-
Ai/Ml系统工程师 CNY 180K-360KControl Systems | Data Feedback | Data Feedback Loop | Data Quality | Deep learningMid-level Full Time深圳23d ago
-
C++ | CUDA | Data parallelism | DeepSpeed | InfinibandEntry-level Full TimeChina24d ago
-
Senior-level Full TimeBeijing Yizhuang, China26d 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27d ago
-
AI Software Engineering Intern CNY 38K-50KAgent Development | Algorithms | Computer Vision | Deep learning | Fine TuningHands-on projects | On-site work | Professional developmentEntry-level Full Time InternshipCHN - Minhang, China27d 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, China28d ago
-
Machine Learning Engineer (Training Optimization) CNY 240K-480KCUDA | Data Types | DeepSpeed | Diffusion Models | Distributed TrainingSenior-level Full TimeBeijing, Beijing, China1mo ago