Zeeshan Jamal

Data Science Graduate | ML Engineer | Building Scalable Data Pipelines with Snowflake & Airflow

Based in: Lahore, PakistanMost recently: Freelance Web Developer, Domino's Pizza (Freelance)

Data Science graduate from Riphah International University with a strong foundation in building end-to-end ML pipelines and scalable data architectures. Proven experience in automating complex data workflows using GitHub Actions, Snowflake, and PySpark. Passionate about bridging the gap between raw data engineering and actionable business insights, from medical image classification to customer churn prediction.

Experience

Freelance Web Developer

Domino's Pizza (Freelance)freelance

Research Assistant / Collaborator

PostDoc Research (China Collaboration)work

Collaborated on a data-driven research project with a PostDoc researcher in China.

Data Scientist Intern

Kinetic Intelligencework

Scraped data for 24,000 US schools across 35 different sports teams.
Automated scraping workflows using GitHub Actions, eliminating the need for local VPNs and manual execution.
Implemented data caching to optimize future data retrieval and prevent redundant scraping.
Processed 24,000 school records
Automated 100% of the scraping execution via GitHub Actions

PythonWeb ScrapingGitHub Actions

Skills

Technical

Python

Pandas

NumPy

Exploratory Data Analysis (EDA)

Data Cleaning

Jupyter Notebook

Apache Airflow

ETL Pipelines

Data Warehousing

Feature Engineering

Data Visualization

Git

GitHub

Google Colab

SQL

PySpark

Snowflake

Scikit-learn

LangChain

Retrieval-Augmented Generation (RAG)

Matplotlib

Statistical Analysis

MySQL

Medallion Architecture

Classification

Predictive Modeling

Model Evaluation

Docker

PyTorch

AI Agents

Areas of expertise

Continuous Learning

Team Collaboration

Time Management

Adaptability

Analytical Thinking

Critical Thinking

Technical Documentation

Research

Projects

AI Student Assistant using Retrieval-Augmented Generation (RAG)

academic

Developed an intelligent university assistant using Retrieval-Augmented Generation (RAG) to answer questions related to admissions, academics, and university policies. Implemented document retrieval, vector search, and LangChain to generate context-aware responses grounded in official university documents. Improved response accuracy by retrieving relevant context before LLM inference, reducing hallucinations compared to relying solely on the language model's internal knowledge.

PythonLangChainRAGVector Database

Customer Churn Prediction using Machine Learning

personal

Built a Customer Churn Prediction model using transactional retail data collected from ECS (Ehsan Chappal Store). Performed data preprocessing, feature engineering, Exploratory Data Analysis (EDA), and model evaluation to identify customers likely to stop purchasing. Generated actionable business insights to support customer retention strategies, targeted marketing campaigns, and data-driven business decisions.

PythonPandasScikit-learnSQL

Content-Based Movie Recommendation Engine

academic

Developed a Content-Based Recommendation System using Natural Language Processing (NLP) techniques to generate personalized movie recommendations. Applied Bag-of-Words, Count Vectorization, and Cosine Similarity to compute similarity scores between movies. Built a lightweight recommendation engine capable of suggesting relevant content based on user preferences.

PythonNLPScikit-learn

Lung Cancer Detection using EfficientNet

personal

Developed a deep learning-based image classification pipeline using EfficientNet to detect lung cancer from CT scan images. Applied image preprocessing, transfer learning, feature extraction, and model optimization techniques to improve classification performance. Evaluated model performance using Accuracy, Precision, Recall, F1-Score, and Confusion Matrix for medical image classification.

PythonTensorFlowEfficientNetComputer Vision

Modern Data Warehouse & Analytics Pipeline

personal

Designed and implemented an end-to-end ETL Pipeline using PySpark to ingest, transform, and load data into Snowflake. Built an Apache Airflow DAG to automate workflow orchestration, enabling scheduled, reliable, and repeatable data processing. Implemented the Medallion Architecture (Bronze, Silver, and Gold layers) to progressively refine raw data into analytics-ready datasets. Designed analytics-ready Gold Layer warehouse tables optimized for Power BI dashboards and Business Intelligence (BI) reporting. Containerized the complete data pipeline using Docker to ensure reproducible deployment and environment consistency.

SnowflakePySparkApache AirflowSQLDockerPower BI