大模型推理架构师
Tasks
- Automate tuning and resource scheduling
- Build AI compilation and model optimization pipeline
- Build AI training and inference infrastructure
- Design end to end AI system architecture
- Develop high-performance inference engine
- Develop performance analysis and observability tools
- Diagnose system failures and bottlenecks
- Implement model compiler and graph optimizations
- Improve GPU and NPU utilization
- Optimize distributed training performance
- Optimize heterogeneous compute kernels
- Optimize large scale distributed training and inference
- Reduce latency and increase throughput
- Validate and deploy new LLM system techniques in production
Perks/Benefits
- N/A
Skills/Tech-stack
Ascend C | C plus plus | C# | CUDA | CUDA kernel | Checkpointing | Communication overlap | Cutlass | Data-parallel | DeepSpeed | Distributed Data Parallel | Distributed data | FSDP | Graph optimization | Infiniband | KV cache | LLVM | MLIR | Megatron | Mixture of Experts | Model compilation | NCCL | NVSHMEM | Offloading | Pipeline parallelism | PyTorch | Python | Quantization | RDMA | RoCE | SGLang | TVM | Tensor Parallelism | TensorRT-LLM | Torch Dynamo | TorchInductor | Transformer | Triton | Triton Compiler | VLLM | Verbs | XLA | Zero
Education
Bachelor of Engineering | Bachelor of Science | Master of Science | PhD
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, CN20h 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 R1d ago