Hi, I'm Kevin 👋

Building AI agents & LLM applications —
on top of years of high-performance systems engineering

What I do

These days I build AI agents and LLM-powered applications — tool orchestration, context engineering, and making agents reliable enough for real production use.

Before that I spent years building performance-critical backend systems: cloud-native infrastructure, high-throughput engines, in-memory platforms. That systems habit stuck — I still sweat the throughput, stability and clean architecture underneath every agent I ship.

Outside of work I test my limits in national programming contests. Every solution below is open-sourced and reproducible.

📦 Open source

Contributor to openclaw , opencode , mastra and unhead , also astro , litellm , TanStack/query and hono — making agent & LLM infrastructure reliable in production.

🏆 Competition record

Result	Contest	Solution
🥇 Champion	11th CCF Big Data & Computational Intelligence Contest 2023 — graph pattern matching	geaflow-match
🥈 2nd / 6506	AliYun Cloud Native Challenge 2023 — Serverless cold-start elasticity	goscaler
🥉 6th	OpenAtom Open Source Contest 2024 — sparse asymmetric banded linear systems (CUDA)	pbicgstab-ilu0
9th / 4404	1st Cloud Native Programming Challenge 2020 — distributed tracing	tianchi_2020_trace
9th / 200	KDD Cup 2024 — paper source tracing (NLP)	pst-kdd2024

🛠️ Toolbox

AI — agent frameworks · LLM applications · RAG · prompt & context engineering Languages — Python · Java (concurrency, JVM) · Go · C++ / CUDA Systems — Kubernetes · RocketMQ / Kafka / MQTT · Spark / Hive

📫 Reach me

· happy to talk about agents, LLM apps, or anything fast and distributed.

---

🇨🇳 中文版

你好，我是 Kevin 👋

构建 AI Agent 与 LLM 应用 ——多年高性能系统工程为底座

我在做什么

现阶段主线是 AI Agent 与 LLM 应用开发：工具编排、上下文工程， 以及让 Agent 在真实生产环境中足够可靠。

此前多年深耕性能敏感型后端系统：云原生基础设施、高吞吐引擎、内存级平台。 系统的习惯留了下来 —— 我依然会为每一个 Agent 背后的吞吐、稳定性与架构洁癖较真。

业余时间通过国家级编程竞赛检验技术上限，所有获奖方案均已开源、可复现。

📦 开源贡献

openclaw 、opencode 、 mastra 、unhead 贡献者， 另有 astro 、litellm 、 TanStack/query 、hono ， 专注让 Agent 与 LLM 基础设施在生产环境更可靠。

🏆 竞赛战绩

成绩	赛事	方案
🥇 冠军	2023 第11届 CCF 大数据与计算智能大赛 · 图模式匹配	geaflow-match
🥈 亚军 (3/6506)	2023 云原生编程挑战赛 · Serverless 冷启动弹性优化	goscaler
🥉 三等奖 (6/47)	2024 开放原子开源大赛 · 非对称不定带宽线性方程组求解 (CUDA)	pbicgstab-ilu0
Rank 9 (9/4404)	2020 首届云原生编程挑战赛 · 分布式链路追踪	tianchi_2020_trace
Rank 9 (9/200)	KDD Cup 2024 · 论文溯源 (NLP)	pst-kdd2024

🛠️ 技术栈

AI — Agent 框架 · LLM 应用 · RAG · 提示词与上下文工程 语言 — Python · Java（并发 / JVM）· Go · C++ / CUDA 系统 — Kubernetes · RocketMQ / Kafka / MQTT · Spark / Hive

📮 联系我

邮箱 pengzh1@qq.com —— 欢迎聊 Agent、LLM 应用，或一切够快、够有趣的东西。