大模型训练与推理Infra工程师-MiMo
Tasks
- Analyze and optimize data loading, communication, and hardware utilization
- Build inference framework for online and offline inference
- Collaborate with research team on training and inference strategy
- Develop distributed training compute platform
- Develop performance monitoring toolchain
- Implement inference optimization techniques
- Integrate high-performance computing technologies
- Maintain distributed training framework
- Optimize inference speed memory usage and energy
- Support product team model deployment
Perks/Benefits
- N/A
Skills/Tech-stack
C plus plus | CUDA | CUDA kernels | CUDNN | DeepSpeed | Docker | GPU | Horovod | JAX | Kubernetes | MPI | Mixed Precision | Mixed-precision training | Model caching | NCCL | NPU | Pruning | PyTorch | Python | Quantization | Ray | TensorFlow | Terraform
Education
Related jobs
-
Entry-level Full Time北京 R1d ago
-
AI基础设施研发工程师（Sandbox / 容器化)-MiMo CNY 180K-420KContainerd | Distributed Systems | Docker | ELK | File SystemMid-level Full Time北京 R1d ago
-
Mid-level Full Time上海、深圳 R4d ago
-
模型部署与推理优化工程师 CNY 180K-360KC++ | Edge inference | Inference Performance | Inference Performance Optimization | Model DistillationMid-level Full Time北京 R10d ago
-
Entry-level Internship上海 R11d ago
-
Entry-level Full Time北京 R13d ago
-
Mid-level Full Time北京 R13d ago
-
Mid-level Full Time北京 R13d ago
-
Ai系统软件实习生 CNY 37K-37KAgent Development | C++ | GPU Computing | HPC | High PerformanceFlexible schedule | Remote workEntry-level Internship上海 R25d ago
-
Mid-level Full Time北京 R28d ago
-
AWS | Azure | JavaScript | NoSQL | Node.jsFast-paced environment | Remote workMid-level Full TimeHangzhou R1mo ago
-
AWS | Agile | Azure | Blockchain | CursorRemote workMid-level Full TimeShenzhen R1mo ago
-
A/B | A/B Testing | AWS | B testing | Cohort AnalysisComprehensive benefits package | Flexible work model | Work from home flexibilityMid-level Full TimeShanghai, China R1mo ago