机器人端侧模型运行与性能工程师
Tasks
- Adapt inference backends and optimize performance
- Build bidirectional streaming inference API
- Create resource scheduling performance and stability feedback loop
- Design and develop robot edge multimodal model runtime system
- Export quantize align precision and improve throughput and latency
- Implement streaming inference cancel abort and timeout
- Integrate TensorRT TensorRT-LLM vLLM SGLang ONNX Runtime and NPU DSP toolchains
- Manage sessions deadline sequence consistency and flow backpressure
- Optimize model splitting lightweight adaptation and edge cloud layered deployment
- Set performance baselines and run tracing regression and long stability tests
Perks/Benefits
- N/A
Skills/Tech-stack
Asynchronous programming | C++ | CUDA | CUDA kernel | FP8 | GRPC | INT4) | INT8 | KV cache | LLM | Linux | Memory Management | Multithreading | ONNX Runtime | Performance Profiling | Python | Quantization | SGLang | Streaming Generation | TensorRT | TensorRT-LLM | Transformer | Triton | VLLM | VLM | WebSocket
Education
Bachelor of Engineering | Bachelor of Science | Master of Science
Roles
AI | AI Performance Engineer | Engineer | Performance Engineer | Software Engineer
Related jobs
-
ARM | Android | Communication Protocols | Core Architecture | DebuggingSenior-level Full TimeShanghai, China5h ago
-
Senior-level Full TimeShanghai, China5h ago
-
Automation & Robotics Engineer CNY 360K-600KActuator integration | Analog Signal | Artificial Intelligence | C++ | CADSenior-level Full TimeHangzhou, China17h ago
-
Data Analytics & Management, AVP CNY 300K-420KAgentic AI | Alteryx | Anomaly Detection | Classification | Code DevelopmentFlexible work/life support | Inclusive development opportunities | Paid volunteer days | Vibrant employee networksExecutive-level Full TimeHangzhou, China17h ago
-
Entry-level Internship上海20h ago
-
Senior-level Full Time上海、北京20h ago
-
Entry-level Internship上海21h ago
-
Mid-level Full Time上海21h ago
-
Mid-level Full Time上海、深圳 R21h ago
-
Mid-level Full Time上海21h ago
-
Senior-level Full Time上海21h ago
-
Mid-level Full Time北京、上海21h ago
-
Entry-level Full Time上海21h ago
-
Entry-level Full Time北京、上海21h ago
-
Mid-level Full Time上海21h ago
-
Mid-level Full Time上海、北京21h ago
-
Mid-level Full Time上海21h ago
-
Senior-level Full Time上海21h ago
-
3D视觉算法工程师 CNY 180K-300K3D Pose Estimation | 3D Reconstruction | 6D Pose | 6D Pose Estimation | Audio ProcessingMid-level Full Time深圳21h ago
-
Senior-level Full Time上海 R21h ago
-
Mid-level Full Time上海 R21h ago
-
Senior-level Full Time上海、北京21h ago
-
Senior-level Full Time上海 R21h ago
-
loco-manipulation（高动态物体交互方向） CNY 180K-360KBody Dynamics | C++ | Contact dynamics | Curriculum learning | Domain RandomizationMid-level Full Time上海21h 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 R21h ago