available for work

Ameer
Hamza
Nasir.

Data Analytics & ML Engineer — turning raw, messy data into end-to-end pipelines, predictive models, and dashboards that actually make decisions easier.

Get in touch → View projects
40K+
records processed
4+
live projects
2026
CS @ GCU Faisalabad
PK
based in Pakistan
JavaScript Docker Shell LLMs Python Pandas Scikit-Learn PyTorch SQL Random Forest Regression Classification Clustering Flask Data Cleaning EDA Feature Engineering Matplotlib Seaborn Streamlit Jupyter Git Kaggle JavaScript Docker Shell LLMs Python Pandas Scikit-Learn PyTorch SQL Random Forest Regression Classification Clustering Flask Data Cleaning EDA Feature Engineering Matplotlib Seaborn Streamlit Jupyter Git Kaggle

// about me

Data is the raw material.
Insight is the product.

I'm a junior Data Scientist and ML Engineer based in Pakistan, currently studying Computer Science at GCU Faisalabad. I build end-to-end ML pipelines — from messy raw datasets all the way to deployed, interactive applications.

My work spans the full analytics lifecycle: data acquisition, cleaning and validation, EDA, model training, evaluation, and deployment. I care about making ML interpretable and useful, not just accurate.

Currently deepening expertise in Deep Learning with PyTorch and actively seeking internship and freelance opportunities in data analytics and ML engineering.

// education

B.S. Computer Science Government College University, Faisalabad Oct 2025 — Present
Relevant Coursework Programming Fundamentals (C++), Calculus & Analytical Geometry, Information & Communication Technologies

// languages

Urdu Native
English Professional Working Proficiency

// capabilities

What I work with

📊
Data Analytics
Data Cleaning EDA Reporting Dashboards Validation
🐍
Python Ecosystem
Pandas NumPy Matplotlib Seaborn Plotly
🤖
Machine Learning
Scikit-learn Random Forest Regression Classification Clustering
🧠
Deep Learning
PyTorch TensorFlow Neural Networks
🗄️
Data & Tools
SQL Jupyter Git Kaggle Docker Shell JavaScript
🚀
Deployment
Flask Streamlit GitHub Pages REST APIs

// selected work

Projects

01 — FEATURED

Free ClaudeCode (CLI)

Built a custom wrapper using ClaudeCode`s API and OpenRouter to create a local LLM inference server. The wrapper supports dynamic prompt templates, context management, and response parsing, enabling seamless integration of LLM capabilities into various applications. 100% FREE no subscription.

ClaudeCode OpenRouter JavaScript Shell Docker
View on GitHub →
git clone https://github.com/ipycharmer/claudecode-free.git
cd claudecode-free
chmod +x run.sh
./run.sh

02

Student Exam Score Predictor

End-to-end ML pipeline trained on 6,607 student records. Predicts exam scores and calculates the minimum weekly study hours needed to pass. Features full data cleaning, Ordinal encoding, MinMax scaling, and a Random Forest model deployed as a Streamlit web app.

Python Scikit-learn Streamlit Pandas Joblib
View on GitHub →
model = RandomForestRegressor( n_estimators=200, random_state=42 ) R² Score: 0.6821 MAE: 2.0341 pts Attendance → 38.5% Hours_Studied → 24.7% Prev_Scores → 8.8%

03

Healthcare EDA & Reporting

Full exploratory analysis on a healthcare Kaggle dataset. Identified outliers, missing data patterns, and key variable correlations. Produced structured visual findings using Matplotlib.

Python Pandas Seaborn Matplotlib
View on GitHub →

04

Deep Learning Experiments

Ongoing neural network experiments using PyTorch. Covers classification tasks, architecture exploration, and training loop design. Actively maintained as skills grow.

PyTorch TensorFlow NumPy Jupyter
View on GitHub →

// experience

Where I've worked

Jan 2025 — Present
FREELANCE · REMOTE

Software Engineer

Self-Employed

  • Delivered 10+ custom automation bots for Discord, Telegram, and Highrise, achieving an 80% client retention rate through tailored solutions.
  • Engineered high-performance, asynchronous versions of yt-dlp and youtubemusicapi in Python to optimize media processing pipelines.
  • Architected a scalable music streaming ecosystem, leveraging a dedicated backend server to fetch and stream audio via custom HTTP APIs.
  • Developed a lightweight Python audio streaming server as a high-efficiency alternative to IceCast, reducing memory consumption to just 18MB for hundreds of concurrent listeners.
  • Managed the full software development lifecycle, focusing on asynchronous programming, backend optimization, and resource-efficient server design.
Jan 2025 — Present
FREELANCE · REMOTE

Data Scientist / ML Engineer

Self-Employed

  • End-to-end delivery of many data science and ML solutions, ensuring high-quality outputs.
  • Executed robust data engineering pipelines using Pandas to clean, transform, and validate diverse datasets, successfully handling thousands of records with complex data inconsistencies.
  • Conducted advanced Exploratory Data Analysis (EDA) on diverse business and behavioral datasets to uncover patterns, generate summary statistics, and drive data-backed insights.
  • Built, tuned, and evaluated predictive models using Scikit-learn, consistently tracking key performance metrics like R^2, MAE, and RMSE to ensure model reliability.
  • Deployed production-ready machine learning models via lightweight web frameworks like Streamlit, successfully managing the complete lifecycle from data acquisition to deployment.

// contact

Let's build
something.

Open to data analytics internships, ML engineering roles, and freelance projects. I respond fast.

hamza6700@gmail.com