Skip to content
View VelimirMueller's full-sized avatar
💭
Coding
💭
Coding
  • Berlin

Block or report VelimirMueller

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
VelimirMueller/README.md
 _   _ _____ _     ___ __  __ ___ ____    __  __ _   _ _____ _     _     _____ ____
| | | | ____| |   |_ _|  \/  |_ _|  _ \  |  \/  | | | | ____| |   | |   | ____|  _ \
| | | |  _| | |    | || |\/| || || |_) | | |\/| | | | |  _| | |   | |   |  _| | |_) |
| |_| | |___| |___ | || |  | || ||  _ <  | |  | | |_| | |___| |___| |___| |___|  _ <
 \___/|_____|_____|___|_|  |_|___|_| \_\ |_|  |_|\___/|_____|_____|_____|_____|_| \_\

Senior Frontend Engineer / Product Engineer / Agentic AI Development / ML Explorer

I translate business requirements into polished UX/UI concepts and ship them with a modern stack. From requirements engineering to branding to deployment -- everything end-to-end.


// skills.json
{
  "frontend":  ["Next.js", "React", "Vue 3", "Nuxt", "TypeScript", "Tailwind CSS"],
  "backend":   ["Node.js", "Quarkus", "FastAPI", "Laravel"],
  "languages": ["TypeScript", "JavaScript", "Python", "Kotlin", "Rust", "WASM"],
  "testing":   ["Jest", "Vitest", "Playwright", "Pytest", "JUnit"],
  "platform":  ["Vercel", "Supabase", "Docker", "GitHub Actions", "AWS", "Nginx"],
  "process":   ["Requirements Engineering", "UX/UI Design", "Branding", "CI/CD"],
  "tools":     ["Figma", "Claude AI", "GPT4All", "Vite", "Webpack"]
}


Currently building

vlm-code-context-mcp - MCP server that indexes codebases into a SQLite database, exposing file metadata, exports, dependency graphs, and per-file change tracking.

I made my AI coding agent argue with a local Gemma 3 model about whether my tool actually works. Then I used the debate to build a statistically rigorous benchmark. Here's what happened. roughly 44% token sabings (and the best part is, claude gets a development history and learns from past mistakes due to the retrospective process after each sprint)

benchmark2

What I'm exploring

  • LLMs and document intelligence
  • Secure auth patterns and scalable backend design
  • Developer-first tools with clean UI/UX
  • Rust + Bevy for game development
  • WebAssembly for performance-critical web features

Philosophy

Good frontend doesn't start with code -- it starts with understanding the business. I analyze requirements, translate them into UX/UI concepts that fit the brand, and plan the project from idea to deployment.



LinkedIn ·  Email ·  Website

Pinned Loading

  1. portfolio-website portfolio-website Public

    My personal portfolio website, highlighting my skill-set

    TypeScript 1

  2. vlm-code-context-mcp vlm-code-context-mcp Public

    MCP server that indexes codebases into a SQLite database, exposing file metadata, exports, dependency graphs, and per-file change tracking.

    TypeScript 4 1

  3. langchain_debater langchain_debater Public

    A multi-role debate agent built with LangGraph + Claude Sonnet 4.6, instrumented with dual tracing to LangSmith and Langfuse. A personal learning playground for getting hands-on with LangChain / La…

    Python 1

  4. claude_development_skills claude_development_skills Public

    Opinionated, audit-aware skills for building scalable, maintainable frontend (and later infra/backend) projects.

    Shell 3

  5. aurorae_ws_chatbot_api aurorae_ws_chatbot_api Public

    GPT4ALL chatbot websocket server - Flask, Docker

    Python 1

  6. cyberpunk_arcade_shooter cyberpunk_arcade_shooter Public

    A cyberpunk arcade shooter built in Rust using the Bevy engine https://bevy.org. Step into a minimalist, glowing world where every shape pulses with danger.

    Rust 1