Tasks:
- * Build model integration and unified gateway
- * Build platform monitoring and alerting
- * Build secure sandbox execution
- * Define platform technical standards and ensure SLOs
- * Deploy and release large language models on Kubernetes
- * Design and develop company-wide Agent platform
- * Develop Function Calling and MCP tool ecosystem
- * Develop multi-Agent orchestration and evaluation
- * Implement canary releases and autoscaling
- * Implement conversation memory and management
- * Improve fault tolerance and troubleshooting
- * Improve platform performance, usability, and stability
- * Optimize model throughput, latency, and resource utilization
Perks/Benefits:
Skills/Tech stack required:
[Agent Orchestration] [API Gateways] [Caching] [Databases] [Distributed Systems] [Function Calling] [Go] [GPU clusters] [Higress] [Inference Optimization] [Istio] [Kubernetes] [Langchain] [Langgraph] [Linux] [LLM Deployment] [LLM Inference] [LLM Inference Optimization] [MCP] [Message Queues] [Microservices] [Observability] [Python] [RAG] [RDMA] [Service Mesh] [SGLang] [SLO Management] [TensorRT-LLM] [VLLM]
Educational requirements:
[Bachelor's Degree] [Master's Degree]
Role(s):
[AI Infrastructure Engineer] [AI Platform Engineer] [Engineer] [Infrastructure Engineer] [Machine Learning Platform Engineer] [Platform Engineer]