大模型端侧部署工程师
Tasks
- Build end to end deployment toolchain
- Collaborate with hardware teams on NPU optimization
- Conduct QAT and PTQ
- Deploy LLM on SoC platform
- Develop conversion calibration and validation scripts
- Document deployment standards and accuracy power testing
- Implement model compression techniques
- Integrate ONNX toolchains and inference accelerators
- Optimize LLM performance for edge
- Optimize data pipeline and compute graph
- Profile CPU NPU GPU and memory bottlenecks
- Quantize convert and deploy models
Perks/Benefits
- N/A
Skills/Tech-stack
ADB Systrace | Ascend ATC | C plus plus | CANN | CI/CD | Docker | Git | Horizon ModelZoo | INT4) | INT8 | Kernel development | Knowledge Distillation | Language Models | Large Language Models | Low-rank decomposition | MLIR | MagicMind | Mixture of Experts | Model Pruning | Model Quantization | NPU Kernel | NPU Kernel Development | Nsight | ONNX | OpenVINO | PTQ | Perf | Performance Profiling | Post-training | Post-training Quantization | PyTorch | Python | QAT | Quantization aware training | RKNN Toolkit | TVM | TensorRT | Weight Sharing
Education
Bachelor of Engineering | Bachelor of Science | Master of Science
Related jobs
-
ARM | Android | Communication Protocols | Core Architecture | DebuggingSenior-level Full TimeShanghai, China4h ago
-
Senior-level Full TimeShanghai, China4h ago
-
Automation & Robotics Engineer CNY 360K-600KActuator integration | Analog Signal | Artificial Intelligence | C++ | CADSenior-level Full TimeHangzhou, China15h ago
-
Senior-level Full Time上海、北京19h ago
-
Entry-level Internship上海19h ago
-
Mid-level Full Time上海、深圳 R19h ago
-
Mid-level Full Time上海19h ago
-
Entry-level Full Time上海19h ago
-
Mid-level Full Time上海20h ago
-
Mid-level Full Time上海、北京20h ago
-
Mid-level Full Time上海20h ago
-
Senior-level Full Time上海20h ago
-
Senior-level Full Time上海 R20h ago
-
Mid-level Full Time上海 R20h ago
-
Senior-level Full Time上海、北京20h ago
-
Data Infra高级研发工程师（AI与具身智能数据平台方向） CNY 144K-240KAsynchronous processing | Automated testing | CI/CD | CRD | Cloud NativeSenior-level Full Time上海 R20h ago
-
Mid-level Full Time北京、上海20h ago
-
Senior-level Full Time上海20h ago
-
Ego-Centric视觉感知算法工程师 CNY 180K-300K2D Segmentation | 3D Gaussian Splatting | 3D Hand Pose | 3D Reconstruction | 6D PoseMid-level Full Time上海、北京 R20h ago
-
Senior-level Full Time上海20h ago
-
Mid-level Full Time上海20h ago
-
Entry-level Full Time深圳20h ago
-
Mid-level Full TimeBeijing21h ago
-
资深机器视觉专家 CNY 180K-300KComputer Vision | Deep learning | Docker | Image Segmentation | Image classificationMid-level Full Time北京、上海21h ago
-
Entry-level Full Time北京21h ago