AI运维工程师(大模型推理 / AI Infra)
Tasks
- Automate operations and maintenance
- Build AI infrastructure
- Conduct model quantization and inference acceleration
- Deploy inference frameworks
- Deploy large model inference services
- Ensure inference stability and reliability
- Implement Kubernetes deployments
- Implement containerized services
- Increase inference throughput
- Manage GPU cluster operations
- Operate and maintain inference services
- Optimize GPU memory utilization
- Optimize inference performance
- Run load testing and troubleshooting
- Set up monitoring and alerting
- Support model rollout and online stability optimization
Perks/Benefits
- N/A
Skills/Tech-stack
Docker | GPU Cluster | GPU Memory Optimization | GPU memory | Inference acceleration | Kubernetes | Linux | Lmdeploy | Memory Optimization | Model Quantization | Monitoring and Alerting | Python | Shell | TGI | TensorRT-LLM | Throughput Optimization | Transformer | VLLM
Education
Related jobs
-
Mid-level Full Time深圳7h ago
-
大模型算法工程师(Memory/RAG/意图识别) CNY 180K-360KARVR | Computer Vision | Data cleaning | Data labeling | Deep learningMid-level Full Time深圳7h ago
-
AI应用研发工程师(架构设计/RAG/Agent) CNY 180K-300KAPI Development | CI/CD | Concurrency | Context Management | Data PipelinesMid-level Full Time深圳7h ago
-
Entry-level Full Time深圳7h ago
-
影像算法工程师 (Ai/Ar 眼镜方向) CNY 216K-300KC++ | Color Space Conversion | Color space | Computer Vision | Deep learningMid-level Full Time深圳7h ago
-
【27届校招】AI Infra 推理优化工程师 CNY 180K-300KDeep learning | Inference Optimization | Knowledge Distillation | Model Compression | ONNXEntry-level Full Time广州、北京、上海7h ago
-
【27届校招】数据运维工程师 CNY 180K-300KBig Data | Docker | Function Calling | Go | Hybrid CloudHands-on practice | MentorshipNone Full Time广州 R7h ago
-
具身智能算法工程师 CNY 25K-37KDeep learning | Distributed Training | GPU Training | IQL | Inference OptimizationInternshipEntry-level Internship北京 R8h ago
-
【27届校招】AI Infra 推理优化工程师 CNY 180K-300KKnowledge Distillation | Model Compression | ONNX | Pruning | PyTorchNone Full Time广州、北京、上海8h ago
-
【27届校招】数据运维工程师 CNY 180K-300KAI Agent | Big Data | Containerization | Function Calling | GoMentorship | On-the-job trainingNone Full Time广州 R8h ago
-
Mid-level Full TimeShanghai, SH, CN, 2000311d ago
-
AI/ML Engineer CNY 240K-360KAWS | Agent Orchestration | Agent systems | Agile Development | CD pipelinesMid-level Full TimeShanghai, SH, CN, 2000311d ago
-
AWS | Azure | Debugging | Docker | GCPEntry-level Internship Part TimeShanghai - Phincas 2, China1d ago
-
Senior Full-stack Engineer (Data & AI) CNY 300K-360KActive Directory | Agile | Angular | Apache Flink | Apache SparkFlexible working environment | Inclusion programs | Learning and development | Well-being supportSenior-level Full TimeChengdu, Manulife Information and Technology Center, …1d ago
-
AI & Data Science Intern CNY 38K-50KAgentic AI | Data Pipelines | Data Preprocessing | Data Visualization | EmbeddingsHands-on project experience | Innovation opportunities | MentorshipEntry-level Full Time InternshipSHANGHAI, China1d ago
-
Entry-level Full Time北京 R1d ago
-
Nlp / Llm 应用工程师 CNY 180K-360KAgent | Anthropic API | Automated testing | Chroma | Dialogue ManagementEntry-level Full Time北京 R1d ago
-
机器人VLA算法研究员 - XiaomiRobotics CNY 500K-500KAction Generation | Deep learning | Diffusion Models | Machine Learning | Mixture of ExpertsEntry-level Full Time北京1d ago
-
VLA训练infra算法工程师 - XiaomiRobotics CNY 240K-480KBF16 | C++ | CPU Memory Networking Fundamentals | CUDA | DeepSpeedMid-level Full Time北京 R1d ago
-
具身世界模型训练INFRA工程师 - XiaomiRobotics CNY 180K-360KAPIs | Deep learning | Distributed Training | Fault Tolerance | LinuxMid-level Full Time北京1d ago
-
具身世界模型推理INFRA工程师 - XiaomiRobotics CNY 240K-480KCFG | Computer Vision | Diffusion Models | Expert parallelism | FP8Senior-level Full Time北京1d ago
-
具身智能算法工程师-模型 CNY 500K-500KActor-critic | Computer Vision | Deep learning | Distributed Training | Implicit Q LearningEntry-level Full Time北京 R1d ago
-
Mid-level Full Time北京1d ago
-
Agent 全栈研发工程师(前/后端)-MiMo CNY 180K-300KAPI Design | Agents SDK | Authentication | Authorization | AutogenMid-level Full Time北京1d ago
-
Mid-level Full Time北京 R1d ago