Abdullah

Python Developer - Web Scraping & Machine Learning

Self Employed • Freelance

Jun 2026 - Present • 2 mos

Freelance Python developer specializing in web scraping and machine learning solutions, with a track record of delivering reliable, production-ready systems for clients across e-commerce, real estate, finance, and research industries. I help businesses turn messy, scattered web data into clean, structured, actionable information — and go further by building machine learning solutions on top of that data. Services I provide: Automated Web Scraping Extracting data from any website — static or JavaScript-heavy dynamic pages — using Python, BeautifulSoup, Scrapy, and Selenium. I handle pagination, login-protected pages, anti-bot measures, and large-scale extraction. Data Delivery in Your Preferred Format Clean, structured data delivered as CSV, Excel, JSON, or directly loaded into a MySQL database, ready for use. Machine Learning Development & Deployment Building and training ML models (classification, regression, clustering) tailored to your problem, then deploying them as production-ready APIs using FastAPI and Docker. Automated Reporting Systems Scheduled, hands-off reporting systems with email alerts and interactive Excel dashboards — insights without manual work. Data Cleaning & Analysis Turning raw, messy data into clean, analysis-ready datasets using Pandas, with clear summaries and visualizations. Featured Project: Amazon Price Tracker Built a fully automated tracker that monitors product prices in real time, detects price drops, sends instant email alerts, and generates Excel reports with historical price trend graphs — a complete, hands-off monitoring system. Why work with me: I deliver working systems, not just scripts — tested, documented, easy to maintain Clear communication with regular updates Experience with both small scraping tasks and full end-to-end data pipelines Let's talk if your project involves data extraction, analysis, or ML.

AI/ML Developer

Freelancer.com • Trabajador autónomo

Jun 2026 - Present • 2 mos

I'm a Python developer and data science practitioner with hands-on, project-based experience across the full AI and machine learning stack — from classical machine learning and deep learning to modern LLM-powered systems like RAG pipelines and AI agents. My work spans building intelligent applications, deploying them into production, and setting up the infrastructure that keeps them running reliably. AI Agents & RAG Systems A major part of my recent work has focused on Retrieval-Augmented Generation (RAG) and AI agent development. I built an AI Employee Copilot for a technology company, trained specifically on their internal service documentation, capable of answering client queries with cited sources, drafting business proposals, summarizing meetings, and assisting internal teams with day-to-day workflows — combining RAG with practical business automation. I've also developed several standalone RAG applications: a system that lets users chat with any public GitHub repository by cloning, parsing, and embedding the entire codebase, enabling natural-language questions about the code with source-cited answers (built with FastAPI and ChromaDB); a research paper assistant that allows users to upload multiple academic papers and ask questions, generate summaries, compare papers, and extract methodology, limitations, and research gaps automatically; and a modular RAG chatbot built with Groq, LangChain, and ChromaDB that lets users upload PDF documents, generate embeddings, and chat with their own documents through a Streamlit interface. Across these projects, I've worked with the full RAG toolchain — document parsing, chunking strategies, embedding generation, vector databases (ChromaDB), retrieval optimization, and integrating LLM APIs (including Groq and other providers) to generate accurate, context-aware, and properly cited responses.