端侧模型部署工程师
Tasks
- Create test cases for deployments
- Deploy deep learning models
- Deploy inference services across platforms
- Develop and optimize CUDA operators
- Develop deployment automation scripts
- Distill models
- Export and convert models for deployment
- Monitor deployed model performance
- Optimize deployment for heterogeneous compute platforms
- Optimize model performance on target hardware
- Package models as inference services
- Prune models
- Quantize models
- Research and implement model compression
- Tune inference for stability and consistency
Perks/Benefits
- N/A
Skills/Tech-stack
C++ | CUDA | DSP | Heterogeneous computing | Inference engine | Knowledge Distillation | Linux | Model Pruning | Model Quantization | NPU | ONNX | ONNX Runtime | OpenVINO | PyTorch | Python | TensorFlow | TensorRT
Education
N/A
Related jobs
-
Mid-level Full Time深圳、上海3h ago
-
Mid-level Full Time北京3h ago
-
机器人大模型软件工程师 CNY 180K-300KAgent systems | Asynchronous programming | C++ | Context Scheduling | Conversation ManagementMid-level Full Time深圳3h ago
-
Mid-level Full Time广州3h ago
-
Mid-level Full Time广州3h ago
-
驾舱一体专家/高级专家/总监 CNY 240K-480KComputer Vision | Data Generation | Data Preprocessing | Data cleaning | Deep learningSenior-level Full Time北京、上海、深圳、广州3h ago
-
Entry-level Full Time深圳、上海、北京4h ago
-
Mid-level Full Time深圳、上海、北京、中国香港4h ago
-
Data Visualization | Data alignment | Data labeling | Data pipeline | Dataset integrationMid-level Full Time深圳、上海4h ago
-
Software Engineer (All Levels) – 大模型与智能机器人系统 CNY 240K-480KC++ | CUDA | DDS | GPU memory | GPU memory managementEntry-level Full Time广州、深圳4h ago
-
Agent systems | LLM | Machine Learning | Multi-Agent | Multi-Agent SystemsMid-level Full Time深圳、上海4h ago
-
Entry-level Full Time InternshipBeijing4h 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4h ago
-
Mid-level Full Time北京6h ago
-
大模型算法专家 CNY 240K-480KAgentic RL | Language Models | Large Language Models | Linux | Multimodal GenerationSenior-level Full Time北京7h ago
-
Entry-level Full Time北京8h ago
-
Senior-level Full Time北京8h ago
-
Senior-level Full Time北京1d ago
-
Senior-level Full Time上海1d ago
-
【算法】多模态/大模型算法专家(上海) CNY 240K-480KAgent Framework | C plus plus | Computer Vision | Language Processing | LinuxSenior-level Full Time上海1d ago
-
【算法】计算机视觉算法专家(上海) CNY 240K-480KAnomaly Detection | C++ | Computer Vision | Deep learning | Fine-grained classificationSenior-level Full Time上海1d ago
-
大模型应用算法工程师/专家 CNY 240K-480KC++ | Computer Vision | Deep learning | Direct Preference Optimization | Human Computer DialogueSenior-level Full Time上海、北京1d ago
-
大模型应用算法实习生 CNY 25K-37KAgentic Systems | C++ | Customer Service | Customer Service Automation | Deep learningOne-on-one mentorship | Technical workshopsEntry-level Internship上海1d ago
-
【算法】计算机视觉算法专家(杭州) CNY 240K-480K3D Vision | Anomaly Detection | C++ | Computer Vision | Image RetrievalSenior-level Full Time杭州1d ago
-
机器学习特征/样本数据工程研发 CNY 180K-300KC++ | Caching | Data Engineering | Data Governance | Feature EngineeringEntry-level Full Time北京、上海1d ago