Python developer building AI/ML tools and automation systems, including bilingual (EN/中文) tools for cross-border e-commerce.

• 🔭 Currently building AI agents, real-time systems, and cross-border tools
• 🌱 Learning: applied ML and production-grade agent systems
• 📍 Based in Lahore, Pakistan
• 💼 Open to remote opportunities in Python / AI-ML / Automation

Bilingual (EN/中文) customer support and listing assistant for cross-border e-commerce, powered by Qwen (Alibaba Cloud Model Studio) — live-tested against the real API.

• Stack: Python, FastAPI, Qwen/DashScope

Fine-tuned YOLOv8 to detect empty shelf space in retail photos, served via FastAPI with a live upload dashboard.

• Stack: Python, FastAPI, YOLOv8/Ultralytics, PyTorch
• Result: mAP@50 0.613 on a held-out validation set, full Colab training notebook included

AI customer support agent using Retrieval-Augmented Generation — answers only from a store's own catalogue and policies, refuses to guess when data doesn't cover a question.

• Stack: Python, FastAPI, sentence-transformers, OpenRouter
• Result: 94% correct behavior, zero hallucinations on a purpose-built eval set

Real-time collaborative kanban board — WebSocket-synced card updates and live presence across multiple clients.

• Stack: Python, FastAPI, WebSockets, SQLAlchemy

Webhook router — verifies, delivers, and automatically retries webhooks (GitHub, Stripe, or custom) with a full delivery audit trail.

• Stack: Python, FastAPI, APScheduler

Self-hosted page-change watcher — schedules checks on any URL, detects changes by content hash, with SSRF protection and JWT auth built in.

• Stack: Python, FastAPI, APScheduler, SQLAlchemy

Languages: Python, TypeScript AI/ML: PyTorch, YOLOv8, RAG pipelines, Qwen, LLM integration Backend: FastAPI, WebSockets, PostgreSQL, SQLAlchemy Other: Docker, GitHub Actions, Git

LinkedIn