Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Appearance settings
View leo-lilinxiao's full-sized avatar
:electron:
Stay
:electron:
Stay

Block or report leo-lilinxiao

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
leo-lilinxiao/README.md

Typing SVG


🌟 About Me

const linxiao = {
  name: "linxiao",
  role: "Algorithm Researcher · AI Infrastructure Engineer",
  company: "AIGCode(蔻町科技)",
  focus: ["Algorithms", "AI infrastructure", "Reliable systems", "Engineering craft"],
};
  • 👋 Hi, I'm linxiao. I enjoy taking algorithms from whiteboard sketches to AI systems that can handle real traffic without losing their cool.
  • 🏢 Currently at AIGCode(蔻町科技). Previously an Algorithm Researcher / Senior Engineer at Huawei Cloud C Lab, where I moved between research, infra, deployments, and keeping systems calm.
  • 🛠️ Much of my favorite work lives inside company products, so this profile is my public workbench: side projects, notes, experiments, and a few things allowed to see daylight.
  • 🏡 Personal site: leo-lilinxiao.github.io
  • 🎮 I do not play much these days, but League of Legends still has a tiny legacy process running in my memory.

Activity Graph

snake animation


📮 Email · Connect


footer

Pinned Loading

  1. codex-autoresearch codex-autoresearch Public

    Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresear…

    Python 2k 115

  2. pie-project/pie pie-project/pie Public

    Pie: Programmable LLM Serving

    Rust 184 26

  3. walkinglabs/modern-llm-notebook walkinglabs/modern-llm-notebook Public

    A hands-on course for building modern LLMs from scratch in PyTorch, with 26 runnable Jupyter Notebooks covering tokenizers, attention, MoE, RLHF, inference, evaluation, and distillation.

    Jupyter Notebook 138 29

Morty Proxy This is a proxified and sanitized view of the page, visit original site.