Lead Engineer, AI Agent Systems
Tasks
- Build checkpointing and interruption resumption
- Build file processing and transfer pipelines
- Build retrieval and knowledge access capabilities
- Build structured task workspaces for dynamic context
- Contribute code to critical platform modules
- Create skill execution and management engines
- Deliver failure recovery and self healing
- Design agent loop runtime and middleware pipelines
- Develop MCP hub infrastructure
- Develop automated evaluation systems and feedback loops
- Develop secure sandboxed environments
- Implement authorization and cost control for long running tasks
- Implement concurrency control and execution scheduling
- Implement hierarchical context budget governance
- Implement multi layer memory and retrieval systems
- Implement multi tenant isolation and security controls
- Lead agent infrastructure architecture and evolution
- Lead architecture decisions and code reviews
- Manage task decomposition and dependency execution
- Orchestrate planning and sub agent workflows
- Own context orchestration design and implementation
- Provide end to end observability and diagnostics
- Standardize inputs and manage dynamic capability representation
- Support long history compression and evidence traceability
- Translate business use cases into reusable platform capabilities
Perks/Benefits
- N/A
Skills/Tech-stack
Agent systems | Asynchronous programming | Authorization | Checkpointing | Concurrency Control | Context compression | Cost Control | Diagnostics | Distributed Systems | Docker | Evidence traceability | Failure recovery | Input Standardization | Kubernetes | LLM | Lifecycle Management | Long Context | Long Context Compression | MCP Hub | Memory systems | Model Context Protocol | Model routing | Multi-model | Multi-model routing | Multi-tenant | Multi-tenant Isolation | Observability | Observability Diagnostics | Python | Retrieval-Augmented Generation | Sandbox Isolation | Security | Self-healing | Streaming | Tenant Isolation | Token budgeting | Tool Lifecycle | Tool Lifecycle Management
Education
N/A
Roles
Related jobs
-
AI software application developers (CG) CNY 84K-120KAI | Algorithms | Benchmarking | C# | C++Career growth | Continuous learning | Onsite workEntry-level Full TimeCHN - Minhang, China21h ago
-
AI Framework Software Engineer - vLLM CNY 300K-420KAsynchronous Communication | C++ | Data parallelism | Deep learning | Distributed SystemsEntry-level Full TimeCHN - Minhang, China21h ago
-
Mid-level Full TimeXian, Shaanxi, China21h ago
-
Mid-level Full TimeShanghai, China21h ago
-
AI Frameworks Engineer - Model and Kernel Optimization CNY 160K-240KC++ | Deep learning | GPU Programming | Kernel development | PyTorchOn-site workSenior-level Full TimeCHN - Minhang, China21h ago
-
AI Framework Software Engineer – PyTorch CNY 74K-100KC++ | Debugging | Deep learning | Distributed Computing | GPU OptimizationOn-site workEntry-level Full TimeCHN - Minhang, China21h ago
-
AI Compiler and Library Engineer CNY 60K-60KAssembly | C# | C++ | Deep learning | JavaCollaborative environment | Hands-on projects | On-site workEntry-level Full TimeCHN - Minhang, China21h ago
-
Mid-level Full Time北京1d ago
-
Miclaw-端云协同调度专家 (Hybrid AI Architect) CNY 144K-240KClaude 3.5 | Consistency protocols | Context Switching | Data Compression | Distributed SystemsHybrid workSenior-level Full Time北京 R1d ago
-
AI基础设施研发工程师（Sandbox / 容器化)-MiMo CNY 144K-240KAlerting | AppArmor | Argo Workflows | CI/CD | CPU SchedulingMid-level Full Time北京1d ago
-
Senior-level Full Time北京1d ago
-
Algorithms | Artificial Intelligence | Concurrency | Containerization | Data StructuresMid-level Full TimeShanghai1d ago
-
Apache Cassandra | Apache Solr | CI/CD | Elasticsearch | JavaSenior-level Full TimeShanghai1d ago
-
Apache Flink | Apache Kafka | Apache Spark | Apache Superset | Data GovernanceMid-level Full TimeShanghai1d ago
-
Machine Learning Engineer CNY 180K-360KAndroid | C# | C++ | Convolutional Neural Network | Deep learningEntry-level Full TimeShanghai, China1d ago
-
.NET 6 | .Net 8 | .Net Framework | Asynchronous programming | C#Mid-level Full TimeChina-Shanghai1d ago
-
Senior-level Full TimeShanghai, Shanghai, China1d ago
-
None Full Time上海2d ago
-
Entry-level Full Time北京2d ago
-
Mid-level Full Time北京2d ago
-
大数据开发工程师 CNY 180K-300KAnomaly Detection | Apache Flink | Apache Spark | Data Governance | Data LakeMid-level Full Time北京2d ago
-
Entry-level Full Time InternshipBeijing2d ago
-
Mid-level Full Time北京2d ago
-
Mid-level Full Time北京2d ago
-
Senior-level Full Time北京、上海2d ago