Skip to content
View adnanahmaddev's full-sized avatar

Block or report adnanahmaddev

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.

Content in all repositories owned by your account will be closed.
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
adnanahmaddev/README.md

Adnan Ahmad | Principal Software Engineer

Website LinkedIn

I am a Principal Software Engineer specializing in AI Engineering, Distributed Systems, Micro-Frontends, and System Scalability. I focus on designing clean architectures, building autonomous AI agents, and scaling high-performance microservices.


πŸš€ Core Competencies

πŸ€– AI Engineering & Agentic Workflows

  • Architecting AI Agents: Designing autonomous, multi-agent systems using framework design patterns (Gemini API, Claude, LangGraph).
  • Text-to-SQL Engines: Building safe, harness-agnostic database query systems powered by Large Language Models.
  • Vision & Multi-modal Integration: Integrating multi-modal LLMs for real-time document and media processing.

🌐 Distributed Systems & Scalability

  • High-Throughput Microservices: Building resilient, low-latency APIs and event-driven backends.
  • Real-Time Systems: Scaling websockets, streaming pipelines, and pub-sub systems for high concurrency.
  • Clean Architecture: Designing modular, testable codebases in TypeScript, Go, and Python.

πŸ› οΈ Featured Open Source Projects

Here are a few select projects representing my work. You can explore the full showcase on my Projects Page.

A dynamic, resolution-independent desktop window layout engine for macOS that enables AI agents to tile, split, and stack windows automatically via AppleScript and a compact column DSL.

  • Keywords: Python 3, AppleScript, macOS System Events, AI Agents, Automation.

An AI-powered diagram studio and interactive visual editor that converts natural language into live Mermaid.js system architecture diagrams, featuring self-healing syntax auto-fix, Monaco editor, and pan/zoom SVG viewport canvas.

πŸ“ Synapse

An open-source AI course generator that generates complete, structured curriculums (modules, lesson content, and interactive quiz checkpoints) from a single prompt. Features a dual-provider model for cloud/local inference (Gemini & Ollama) and an offline-first data layer with IndexedDB caching and auto-sync queue to MongoDB.

  • Keywords: Next.js, TypeScript, Gemini API, Ollama, IndexedDB, MongoDB.
  • Website Detail: Read the deep dive article: Building Synapse.

A production-grade, IDE/agent-harness agnostic, and database-agnostic Python library that translates natural language queries into safe SQL statements and executes them against a database, with a built-in strict safety layer and automatic Azure Active Directory (Entra ID) token authentication support.

πŸ“ StudyPal

An agent-native, AI-powered personalized learning companion. Features RAG knowledge hubs for document Q&A, adaptive custom quizzes, mind-mapping tools, and Manim-powered visual math animations.

  • Keywords: Next.js Β· FastAPI Β· PostgreSQL Β· local LLMs (Qwen2.5 / Gemma4) Β· CopilotKit LangGraph, Manim Β· Vocal Bridge.
  • Website Detail: Read the deep dive article: Agent-Native Systems with StudyPal.

A utility to automatically remove digital watermarks from videos generated by Google Gemini, restoring them to a clean, watermark-free state.

  • Keywords: Gemini Vision, Video Processing, Python, numpy, opencv-python, FFmpeg.

A client-side browser extension that dynamically blocks subscription prompts, banner ads, and marketing overlays on DataCamp, providing an uninterrupted focus mode for students.

  • Keywords: Chrome Extension, Manifest V3, Browser Extension.

πŸ“„ Latest Articles & Thoughts

I write about AI, system architecture, and modern engineering practices. Read them on my Blog:


πŸ“¬ Get in Touch

Pinned Loading

  1. StudyPal StudyPal Public

    Intelligent learning assistant built with Next.js, FastAPI, PostgreSQL, and local LLMs (Qwen2.5/Gemma4). Features CopilotKit, LangGraph, Manim, and Vocal Bridge.

    Python

  2. mermaid-ai mermaid-ai Public

    AI-powered diagram studio & interactive visual editor built with Next.js 15, Monaco Editor, Mermaid.js v11 & Google Gemini API for natural language diagramming.

    TypeScript 2

  3. synapse synapse Public

    An open-source AI course generator creating structured curriculums from a single prompt with dual-provider cloud/local inference (Gemini & Ollama) and offline-first data sync.

    TypeScript 8 1

  4. harness-agnostic-text-to-sql harness-agnostic-text-to-sql Public

    A safe, secure, and harness-agnostic Text-to-SQL engine for LLM-powered AI agents. Safely translate natural language into database queries with robust validation.

    Python

  5. window-manager-skill window-manager-skill Public

    Dynamic macOS desktop window layout manager for AI coding agents. Supports 2/3-column tiling, 50/50 vertical stacking, and zero external dependencies.

    Python

  6. gemini-watermark-remover gemini-watermark-remover Public

    Light-weight utility leveraging Google Gemini Vision models to detect, analyze, and remove video watermarks programmatically using Python, numpy, opencv-python, and FFmpeg.

    Python