_{EN  ⇄  中文}

_{I build the infra that makes LLM agents reliable in production — inference serving, MCP tool layers, multi-agent orchestration, and eval/observability.}

How my agents run

_{Every tool call and LLM span is traced; guardrails gate actions; eval feedback closes the loop — agents as observable, cost-bounded systems on a cloud-native substrate.}

Capabilities

Tech stack

Journey

Selected work

• Bison — Enterprise GPU billing & multi-tenant platform
• Inference Cookbook — Inference frameworks, deep-dived
• Cloud Native Cookbook — Cloud-native engineering, deep-dived