Skip to content
View harrisliangsu's full-sized avatar
🤣
🤣
26 followers · 22 following
  • Fliggy
  • Hangzhou
  • 15:41 (UTC -12:00)

Achievements

Achievement: YOLOAchievement: Arctic Code Vault Contributor

Achievements

Achievement: YOLOAchievement: Arctic Code Vault Contributor

Block or report harrisliangsu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
harrisliangsu/README.md

Hi 👋, I'm Harris

AI Application Developer · LLM Agent Builder · from China

harrisliangsu

  • 🤖 Now mainly working on AI application development: LLM Agents, RAG, Multi-Agent orchestration, MCP tooling

  • 🛠️ Daily drivers: Claude Code / Claude Agent SDK, MCP, LangChain, Spring AI

  • 🌱 Currently learning: Agent architecture, Context Engineering, model fine-tuning & inference optimization

  • 💼 Long-time backend engineer (Java / Spring microservices, search & data platforms) — bringing those chops into AI apps

  • 📫 How to reach me sharkchili.su@gmail.com

AI Stack:

AI Stack

Backend & Infra:

Backend & Infra

Pinned Loading

  1. claude-update claude-update Public

    Run `claude update` and read what actually changed — per-version pager, prerelease-aware, with the CHANGELOG fetched in parallel.

    Shell 2

  2. ai-agent-engineer-handbook ai-agent-engineer-handbook Public

    AI Agent / LLM 应用工程师面试与学习手册：四层工程深度长文（Prompt → Context → Agent → Harness）+ 求职实战（中外大厂真实 JD 拆解 + 86 道高质量面试题与答案）

    HTML 2

  3. dark-tech-style dark-tech-style Public

    Dark tech-style design system for Claude Code / Claude.ai — turns one-line requests into consistent dark-themed architecture pages, dashboards, and technical landings.

    CSS 1

  4. llm-finetune-study llm-finetune-study Public

    Hands-on local LLM fine-tuning course (SFT / LoRA / PEFT / DPO / QLoRA) with a browser studio that visualizes loss, tensors, and adapter diffs.

    HTML 1