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
-
Big Data Engineer CNY 156K-240KAgile | Amazon EMR | Amazon S3 | Apache Airflow | Apache HadoopClubs and communities | Employee learning and development opportunities | Gym classes | On-site mealsSenior-level Full TimeWuxi, CN21h ago
-
Entry-level Full Time合肥1d ago
-
None Full Time上海1d ago
-
Apache Flink | Apache Iceberg | Apache Spark | CI/CD | DockerMid-level Full TimeShanghai R1d ago
-
Apache Flink | Apache Iceberg | Apache Spark | CI/CD | DatabasesMid-level Full TimeShanghai R1d ago
-
Mid-level Full Time北京1d ago
-
None Full Time上海1d ago
-
校招-Ai数据产品经理 CNY 144K-240KAgentic Workflows | Data Modeling | Knowledge graph | Ontology Modeling | Plan and SolveSenior-level Full Time上海1d ago
-
None Full Time北京、上海1d ago
-
Entry-level Full Time上海1d ago
-
Ai算法工程师 CNY 144K-240KDeep learning | Feature Engineering | Hadoop | Hive | Human-Computer InteractionEntry-level Full Time深圳1d ago
-
【中台】后端开发专家（Ai 方向） CNY 144K-240KAsynchronous Queue | Caching | Code review | Distributed Systems | Function CallingSenior-level Full Time上海1d ago
-
AI Infra工程师-算法研发方向 CNY 180K-300KC++ | CI/CD | CUDA | Data parallelism | Distributed TrainingMentorshipMid-level Full Time北京、上海1d ago
-
Mid-level Full Time北京、上海1d ago
-
Mid-level Full Time北京、上海1d ago
-
Ai技术专家 CNY 144K-240KAPI Development | Access Control | Agent systems | Code Development | Content SafetySenior-level Full Time上海1d ago
-
Associate Director, Data and Analytics Specialist CNY 510K-510KAgentic AI | Authentication | Authorization | CI/CD | Data StoresMid-level Full TimeGuangzhou, Guangdong, China1d ago
-
Senior Software Engineer(IC3 Data Platform) CNY 480K-540KAgent workflows | Airflow | Apache Flink | C# | C++Senior-level Full TimeChina, Jiangsu, Suzhou; China, Beijing, Beijing; …1d ago
-
Data Services Engineer CNY 160K-264KAWS | Alerting | Alibaba Cloud | Amazon Aurora | Amazon ElastiCacheSenior-level Full TimeShanghai1d ago
-
Senior Machine Learning Engineer CNY 360K-510KBandits | C++ | Deep learning | Distributed Systems | Graphical ModelsSenior-level Full TimeShanghai1d ago
-
Associate Director, Data and Analytics Specialist CNY 510K-510KAPI Development | Agentic AI | Authentication | Authorization | CI/CDMid-level Full TimeGuangzhou, GD, CN, 5106201d ago
-
Clustering | Convolutional Neural Network | Decision Tree | Deep learning | Language ModelsMid-level Full TimeAIA AI Tech ED (Shanghai) Hongkou, …1d ago
-
Apache Flink | Apache Iceberg | Apache Spark | CI/CD | DockerEntry-level Full TimeShanghai R1d ago
-
CI/CD | Docker | Flink | Go | IcebergEntry-level Full TimeShanghai R1d ago
-
Apache Flink | Apache Iceberg | Apache Spark | CI/CD | DockerSenior-level Full TimeShanghai R2d ago