AI Infra SRE 工程师(大模型推理)(深圳/北京)
Core
Ensuring end-to-end stability for large model online inference services, including performance tuning, capacity operations, and observability体系建设.
Role type
Senior SRE specializing in large model inference infrastructure
Builds
Stable, high-performance inference clusters for large language models
Domain
Artificial Intelligence / Large Language Models / Cloud Infrastructure
Deliverable
production ML models
Required skills
Go, Python, Kubernetes, vLLM, SGLang, GPU resource management, KV Cache optimization, capacity planning, observability (SLI/SLO), incident management
Preferred skills
Experience with tidal scheduling, cost optimization, automated self-healing scripts
Technologies
Kubernetes, vLLM, SGLang, GPU clusters
Responsibilities
Monitor and optimize inference service performance and capacity; Build observability systems for latency and resource metrics; Maintain inference clusters and manage deployment strategies; Develop SRE toolchains and automation scripts to reduce manual operations
Seniority
Mid-level, hands-on IC
