Staff Machine Learning Engineer, ML Infrastructure - Online
CNY 360K-600K (estimate) Senior-level Full Time
Tasks
- Automate model packaging and deployment workflows
- Build and improve model serving systems
- Build autoscaling and self healing capabilities
- Design online inference infrastructure for low latency and reliability
- Develop model deployment and validation infrastructure
- Implement dynamic batching and request scheduling
- Implement traffic splitting and rollback
- Improve observability for online ML systems
- Lead architectural improvements for scalability and cost efficiency
- Optimize inference performance
- Set up canary testing and A B experimentation
Perks/Benefits
- Commute subsidy
- Disability insurance
- Employee stock ownership
- Generous vacation
- Health insurance
- Life insurance
- Mental health & wellbeing programs
- Retirement plan
- Training and development programs
Skills/Tech-stack
A/B | A/B Experimentation | Autoscaling | Caching | Canary testing | Deployment Automation | Distributed Systems | Dynamic batching | Error Rate Monitoring | Error rate | GKE | GPU Acceleration | GPU Kernel | GPU kernel optimization | Google Kubernetes | Google Kubernetes Engine | Inference Server | Kernel optimization | Kubernetes | Kubernetes Engine | Latency optimization | Model Validation | Model compilation | Monitoring | NVIDIA Triton | NVIDIA Triton Inference | NVIDIA Triton Inference Server | Observability | PyTorch | Python | Quantization | Rate monitoring | Ray | Ray Serve | Rollback | Runtime tuning | TensorFlow Serving | Throughput Optimization | Torchserve | Traffic splitting | Triton Inference | Triton Inference Server
Education
N/A
Related jobs
-
Mid-level Full Time深圳9h ago
-
Entry-level Full Time北京9h ago
-
Robot Learning 模型全栈工程师 / 研究员 CNY 180K-300KAblation Study | Data Visualization | Data cleaning | Distributed Training | Hyperparameter TuningNone Full Time深圳、北京10h ago
-
Ai应用开发工程师（Pc方向） CNY 144K-240KCost Optimization | Data cleaning | Embedding | Engineering Automation | EvaluationEntry-level Full Time上海10h ago
-
Apache Flink | Apache Kafka | Apache Spark | Apache Superset | JavaMid-level Full TimeShanghai20h ago
-
Apache Flink | Apache Kafka | Apache Spark | CI/CD | Data PipelinesMid-level Full TimeShanghai20h ago
-
Algorithms | Concurrency | Containerization | Data Structures | DebuggingSenior-level Full TimeShanghai20h ago
-
AI RMF | AI Safety | Adversarial Testing | Artificial Intelligence | Automated EvaluationMid-level Full TimeGuangzhou, Guangdong, China21h ago
-
CI/CD | Cassandra | Concurrency | Distributed Systems | ElasticsearchSenior-level Full TimeShanghai23h ago
-
AWS | Access Control | Authentication | Azure | CI/CDEmployee networks | Flexible work/life support | Inclusive development opportunities | Paid volunteer daysMid-level Full TimeHangzhou, China1d ago
-
Senior Software Engineer (GenAI Agent platform) CNY 510K-510KBest practices | Engineering Best Practices | Go | Integration Patterns | JavaSenior-level Full TimeGuangzhou, GD, CN, 5106203d ago
-
【2026届春招】AI Infra工程师-算法研发方向 CNY 144K-240KC++ | CUDA | Data parallelism | Distributed Training | HuggingfaceEntry-level Full Time北京、上海 R3d ago
-
Mid-level Full Time北京3d ago
-
Entry-level Internship北京、上海3d ago
-
【校招实习生】AI Infra 工程师-算法研究方向 CNY 25K-37KC++ | CI/CD | CUDA | NCCL | OpenMPIFull-time internship | Open source project opportunitiesEntry-level Internship北京、上海 R3d ago
-
【校招实习生】感知算法工程师 CNY 25K-37KBEV | C plus plus | CenterNet | Computer Vision | DETRInternship opportunityEntry-level Internship北京、上海3d ago
-
Omni模型算法实习生 CNY 25K-37KAblation Study | Annotation Validation | Cross-modal alignment | Data Analysis | Data AnnotationEntry-level Internship北京、深圳3d ago
-
【27届校招】Omni模型算法工程师/研究员 CNY 500K-500KData Engineering | Distributed Training | Inference acceleration | Instruction Tuning | Knowledge DistillationEntry-level Full Time深圳、上海、北京3d ago
-
Mid-level Full Time深圳、北京3d ago
-
Entry-level Full Time深圳3d ago
-
None Full Time深圳 R3d ago
-
【27届校招】具身数据infra工程师 CNY 144K-240KAI Coding Agent | AI coding | API Design | Access Control | Code reviewMid-level Full Time深圳、上海、北京3d ago
-
None Full Time深圳、上海、广州3d ago
-
Omni模型算法实习生 CNY 25K-37KAblation Study | Cross-modal alignment | Data Analysis | Data Annotation | Dataset cleaningEntry-level Internship北京、深圳3d ago
-
【27届校招】Omni模型算法工程师/研究员 CNY 500K-500KContext modeling | Data Engineering | Distributed Training | End to End | End to End GenerationEntry-level Full Time深圳、上海、北京3d ago