Zainab Fatima

Computer Vision Engineer | AI/ML | Data Science | CS NED’26

Karāchi, Sindh, Pakistan

About

I’m a Computer Science student at NED University (Class of 2026), passionate about building intelligent, data-driven systems that solve real-world problems. My work focuses on creating interactive tools such as dashboards, diagnostic apps, and NLP-based assistants, using technologies like Streamlit, Python, Hugging Face, and geospatial APIs. I’ve consistently maintained strong academic performance alongside hands-on experience in machine learning, data visualization, and natural language processing. I enjoy turning complex data into actionable, user-centered insights and bring a product-thinking mindset to AI, aiming to design solutions that are not just technically sound but also intuitive and impactful.

Experience

  • Computer Vision Engineer at CCRIPT Agency
    Jan 2026 - Present · 6 mos

  • Computer Vision Engineer at Neuralogic
    Jan 2026 - Present · 6 mos

  • Teaching Assistant at Computer Science & Information Technology - NEDUET
    Aug 2025 - Dec 2025 · 5 mos

  • Data Science Intern at 10Pearls
    Jun 2025 - Aug 2025 · 3 mos

    AirLens - Smart Air Quality Companion Designed and developed AirLens, an end-to-end platform for real-time AQI monitoring and 72-hour forecasting. Built the FastAPI backend and Streamlit dashboard, integrated tree-based ML models (ExtraTrees, XGBoost, CatBoost, LightGBM), and implemented a CI/CD pipeline with GitHub Actions for automated data ingestion, feature engineering, model retraining, and deployment. Deployed using Docker with lightweight optimization, powered by Hopsworks Feature Store for scalable data management.

  • Data Science Intern at National Center in Big Data and Cloud Computing (NCBC)
    Dec 2024 - Apr 2025 · 5 mos

    Developed interactive data visualization tools using Streamlit and Hugging Face for population analysis, water monitoring, forest change detection, and watershed delineation. Processed and visualized geospatial and environmental data using Python, Pandas, and Geospatial APIs, optimizing real-time insights and usability.