大模型应用架构师
Tasks
- Build model gateway and adapter layer
- Build reusable agent development framework SDK and components
- Collaborate cross functionally to deliver product from requirements to launch
- Deploy high availability observable and canary services
- Design AI Agent application architecture
- Develop MCP skill tool framework
- Develop core agent modules
- Engineer inference planning decision capabilities for production services
- Implement concurrency control and rate limiting
- Implement error tolerance cost governance
- Implement knowledge base services
- Implement task planning and execution engine
- Implement timeout fallback and degradation
- Integrate inference engines with model gateway and scheduling
- Monitor first token and end to end latency
- Optimize agent pipeline performance and stability
- Track LLM MLLM and agent application trends
Perks/Benefits
- N/A
Skills/Tech-stack
Agent Frameworks | C++ | Caching | Canary Deployment | Concurrency Control | Coze | Dify | Execution Engine | Fallback mechanisms | Function Calling | Go | High Availability | Inference engine | Java | Kafka | LLM Inference | Langchain | Langgraph | Language Models | Large Language Models | Llamaindex | MCP | Model Scheduling | Model gateway | MongoDB | MySQL | Observability | Python | Rate Limiting | Redis | Retrieval-Augmented Generation | SGLang | Streaming | Task planning | TensorRT | TensorRT-LLM | Timeout handling | Token Management | VLLM | Vector Databases | Vector Search
Education
N/A
Related jobs
-
优才-多模态交互算法工程师-X-Lab CNY 240K-480KAttention | Benchmarking | Computer Vision | Deep learning | Hard Negative MiningSenior-level Full Time上海、深圳11h ago
-
Mid-level Full Time深圳 R11h ago
-
Mid-level Full Time北京 R12h ago
-
大模型算法研究员-MiMo CNY 500K-500KActive Learning | C++ | Curriculum learning | Data Generation | Data ProcessingEntry-level Full Time北京12h ago
-
Miclaw-端云协同调度专家 (Hybrid AI Architect) CNY 240K-360KAPI Integration | Consistency protocols | Distributed Systems | Language Models | Large Language ModelsHybrid workSenior-level Full Time北京 R13h ago
-
Mid-level Full Time武汉13h ago
-
Forward Deployed AI Engineer CNY 72K-96KAWS | Agile | Amazon Redshift | BigQuery | Cloud platformTravel up to 50 percentEntry-level Full Time Internship北京14h ago
-
Mid-level Full Time北京 R14h ago
-
Mid-level Full Time Temporary北京14h ago
-
Mid-level Full Time北京 R14h ago
-
Mid-level Full Time杭州14h ago
-
Regional Data & AI Engineer, Operations, Asia Pacific CNY 300K-380KArtificial neural networks | Clustering | Data Architecture | Data Governance | Data ModelingMid-level Full TimeShanghai, CN1d ago
-
[Pricing Data Engineering ] Staff Data Engineer I CNY 120K-180KAWS | Algorithms | Amazon EMR | Apache Airflow | Apache SparkSenior-level Full TimeShanghai, China1d ago
-
Magnetic Recording Algorithm Development Engineer CNY 144K-240KAlgorithm Development | Automated Test | Automated Test Equipment | C# | C++Senior-level Full TimeShenzhen, Guangdong Province, China1d ago
-
Mid-level Full TimeWuxi - Ximei Road, China (Mainland)1d ago
-
Mid-level Full TimeChina, Shanghai1d ago
-
Senior AI Training Performance Engineer CNY 144K-240KC++ | CUDA | Computer Architecture | Deep learning | GPU ArchitectureSenior-level Full TimeChina, Shanghai1d ago
-
Mid-level Full TimeShenzhen, Guangdong, China1d ago
-
Senior-level Full TimeCN-OCG International Center, Cheng Du, China1d ago
-
Sr. System Software Engineer CNY 240K-480KAAC | ARM | ARM Drivers | Audio Encoding | BashOn-site support | Remote support | Technical trainingSenior-level Full TimeChina Shanghai1d ago
-
数据开发工程师 CNY 120K-180KBI | Data Governance | Data Quality | Data Warehousing | Data quality monitoringMid-level Full Time深圳1d ago
-
MiMo-大模型训练框架开发工程师 CNY 240K-480KC++ | CI/CD | DeepSpeed | Distributed Training | GPU Memory OptimizationEntry-level Full Time北京 R1d ago
-
Senior-level Full Time北京1d ago
-
Entry-level Full Time北京 R1d ago
-
Mid-level Full Time北京 R1d ago