SuperMarioYL

_{EN ⇄ 中文}

Leo — AI systems, made to run in production.

_{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

User → Orchestrator → Tools/MCP + Memory/RAG → Inference, on a Cloud Native AI substrate, instrumented by Eval & Observability

_{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

AI Agent: plan→act→reflect loop · Cloud Native: scheduler + pods · Inference: lower latency, higher throughput

Tech stack

Journey

From infrastructure to agents: Cloud Native AI → Inference Acceleration → AI Agent

Selected work

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

Profile views