Pythonscikit-learnMLflow
Telecom Churn Prediction
Production-grade telecom churn prediction system: a config-driven scikit-learn pipeline with SHAP explainability, MLflow experiment tracking and FastAPI serving, trained on…
Building reliable data & AI systems
Muhammad Farooq
Data Engineer · AI Engineer · Data Scientist
01 · About
From raw data to reliable, production-grade systems.
I’m Muhammad Farooq (also known as Muhammad Farooq Shafi), a data engineer and machine learning practitioner focused on building systems that hold up under real scrutiny — not just notebooks that ran once. My work spans the full data lifecycle: ETL pipelines with automated data-quality gates, dbt-modeled analytics warehouses backed by dozens of automated tests, and ML systems evaluated honestly against real baselines rather than a single flattering metric. I’ve built and deployed projects across intrusion detection, recommendation systems, NLP triage, demand forecasting, and computer vision — each one served through a real API or interface, versioned, and tested, not left as a one-off script. I write regularly about the engineering discipline behind trustworthy data work: honest evaluation, reproducible pipelines, and deployment done right.
Muhammad Farooq
Data Engineer · AI Engineer · Data Scientist
0
Projects shipped
0
Certifications
0
Roles & simulations
02 · Tech Stack
Tools I use to move data — and make it useful.
Data Engineering
Python
92%
SQL
90%
Apache Spark
78%
Apache Airflow
80%
Kafka
70%
dbt
82%
ETL / ELT
88%
Data Warehousing
85%
Cloud & Platforms
Snowflake
75%
Databricks
72%
Azure
76%
AWS
74%
GCP
68%
Docker
84%
Kubernetes
65%
Linux
80%
AI & Machine Learning
Machine Learning
88%
Deep Learning
75%
TensorFlow
72%
PyTorch
74%
Scikit-learn
90%
LLMs & RAG
78%
LangChain
70%
Generative AI
80%
Analytics & Tools
Pandas / NumPy
92%
Power BI
70%
Tableau
68%
Excel
85%
FastAPI
80%
Streamlit
78%
Git & GitHub
90%
OpenCV
65%
03 · Selected Work
All projects →
Projects built to run in production, not just in a notebook.
PythonSQLETL
Marketing Analytics Data Pipeline
An end-to-end marketing analytics data pipeline that ingests, transforms and models campaign data for reporting.
PythonRAGLLMs
Knowledge-Base Search (RAG)
A knowledge-base search system built with retrieval-augmented generation for accurate, grounded question answering.
PythonTime SeriesForecasting
Energy Demand Forecasting
A time-series forecasting system for energy demand, built for planning and load-balancing use cases.
PythonGraph AnalysisNetworkX
Organizational Network Analysis
Graph-based analysis of organizational networks to surface influence, collaboration and communication patterns.
Pythonscikit-learnMachine Learning
Fraud Detection System
A classical machine learning system for detecting fraudulent transactions with a focus on precision/recall trade-offs.
04 · Open Source
Building in public.
A live snapshot of my GitHub activity — commits, streaks and languages.
View GitHub profile →
05 · Experience
Where I've applied it.
-
Apr 2025 – Aug 2025 · Remote
Machine Learning Engineer — CodeAlpha
Machine Learning Engineer (Internship) · CodeAlpha
Developed and implemented machine learning models for real-world applications using Python, TensorFlow and scikit-learn. Performed data preprocessing, feature selection and model tuning, and collaborated with cross-functional teams to integrate ML solutions into existing products.
-
Jun 2025 – Aug 2025
Data Science Intern — Arch Technologies
Data Science Intern (Internship) · Arch Technologies
Assisted in data collection, cleaning and preprocessing to support machine learning projects. Developed and tested predictive models using Python and libraries including scikit-learn and pandas, and created data visualizations to communicate insights.
-
May 2025 – Aug 2025 · Hybrid
Data Science Intern — Oasis Infobyte
Data Science Intern (Internship) · Oasis Infobyte
Supported data preprocessing, feature engineering and exploratory data analysis for ongoing machine learning projects, and assisted in building and evaluating predictive models with scikit-learn and pandas.
-
Jun 2025 – Aug 2025 · Remote
British Airways — Data Science Job Simulation
Data Science Job Simulation (Forage) · British Airways
Scraped and analysed customer review data to uncover findings, and built a predictive model to understand the factors that influence buying behaviour.
-
Jan 2025 – Jul 2025 · Remote
BCG X — Data Science Job Simulation
Data Science Job Simulation (Forage) · BCG X
Completed a customer churn analysis simulation, conducting data analysis in Python (pandas, NumPy), engineering and optimizing a random forest model that achieved a 50% recall rate in predicting churn, and delivering an executive summary of findings.
-
Apr 2025 – Aug 2025
Commonwealth Bank — Introduction to Data Science Job Simulation
Data Science Job Simulation (Forage) · Commonwealth Bank
Built data engineering pipelines to aggregate and extract insights from datasets, applied anonymization for data-privacy compliance, and proposed data analysis approaches for well-structured, efficient databases.
-
Oct 2024 – Jul 2025 · Remote
Deloitte Australia — Data Analytics Job Simulation
Data Analytics Job Simulation (Forage) · Deloitte
Completed a job simulation involving data analysis and forensic technology, created a data dashboard using Tableau, and used Excel to classify data and draw business conclusions.
-
Feb 2025 – Jul 2025
Quantium — Data Analytics Job Simulation
Data Analytics Job Simulation (Forage) · Quantium
Developed expertise in data preparation and customer analytics using transaction datasets, identified benchmark stores for uplift testing, and created reports for informed, evidence-based strategic decisions.
-
Jul 2025 · Remote
Lloyds Banking Group — Data Science Job Simulation
Data Science Job Simulation (Forage) · Lloyds Banking Group
Completed a Forage job simulation for Lloyds Banking Group's data science team.
06 · Education
Foundations.
Riphah International University
Bachelor's degree, Artificial Intelligence
Jul 2023 – May 2027
Focused on the design, development and deployment of AI-driven systems. Coursework and projects covered machine learning, deep learning, computer vision, natural language processing and robotics, with hands-on expertise in Python, TensorFlow and PyTorch.
Virtual University of Pakistan (VU)
Associate's degree, Data Science
Apr 2024 – Mar 2026
Developed a strong foundation in data analysis, statistics, programming and machine learning.
Allama Iqbal Open University (AIOU)
Associate's Degree, Business Administration and Management
Jun 2025 – Jun 2026
Participated in business case studies, management discussions and leadership development activities focused on strategy, marketing and organizational management.
07 · Certificates
Google
Always learning, always shipping.
IBM Generative AI Engineering
IBM · Credential ID MFXW3LL9UI6G
Introduction to AI
Google · Jun 2025
IBM AI Engineering Professional Certificate (V3)
Coursera · Jun 2025
Data Analysis with Python
Coursera
IBM Deep Learning with PyTorch, Keras and TensorFlow
IBM · Jun 2025 · Credential ID FVMJDQSAUDL6
AI for Beginners
HP LIFE · Feb 2025
Data Science & Analytics
HP LIFE · Mar 2025
Google AI Essentials
Hands-On Python Machine Learning with Real World Projects
Udemy
Effective Presentation
HP LIFE · Feb 2025
Effective Leadership
HP LIFE · Feb 2025
Master Class on Data Science using Python A-Z for ML
Udemy · Nov 2024
AI Essentials: Introduction to Artificial Intelligence
Udemy · Nov 2024
Data Structures Using Python
Udemy
08 · Services
How I can help.
Data Pipeline & ETL/ELT Engineering
Design and build reliable, monitored pipelines that move data from source systems into warehouses and marts, ready for analytics.
What this covers
- Ingesting raw exports and source data into a repeatable pipeline
- Validating data before it is loaded: schema, null and business-rule checks
- Modeling clean data into a star-schema warehouse and SQL marts
- ELT with dbt, with automated tests that run on every build
- Dashboards or a read-only API on top, so stakeholders can use the data without writing SQL
Tools used across this work: Python, SQL, dbt, DuckDB and Streamlit.
How I approach it
Bad data should be caught at the gate, not discovered three reports later. Raw data passes through validation checks before it reaches the warehouse. Every model is covered by automated tests, so a broken pipeline fails loudly instead of shipping wrong numbers to a dashboard. Transformation logic is written once and re-run on every new data drop, so reporting stays consistent instead of drifting between manual edits.
Work that shows it
- Retail ETL Warehouse: a validated data-quality gate in front of a star-schema warehouse, with a read-only analytics API.
- Olist E-Commerce Analytics Engineering: a dbt star schema on DuckDB over 99,441 real orders, with 34 automated tests and a Streamlit dashboard.
- Retail Analytics Warehouse: a dbt and DuckDB ELT pipeline with 35 automated data-quality tests.
- Marketing Analytics Data Pipeline: raw campaign exports turned into clean, query-ready tables.
- Marketing Attribution Warehouse: a warehouse and pipeline supporting multi-touch attribution.
Choosing the right approach
Whether a pipeline should transform data before or after loading depends on masking needs, compute and who owns the logic. I explain the trade-offs in ETL vs ELT: how to choose between them, and cover rerun safety in idempotent data pipelines.
Work with me
If you have data scattered across exports or systems and need it in one trustworthy place, get in touch with a short description of your sources, where the data should end up, and what reporting you need.
Cloud Data Warehousing
Model and deploy star-schema warehouses on Snowflake, Databricks or DuckDB with automated data-quality testing.
Related reading: Data warehouse vs data lake vs lakehouse: how to choose.
Machine Learning & MLOps
Train, explain and serve ML models with MLflow tracking and FastAPI/Docker deployment.
Analytics & Dashboards
Turn raw data into decision-ready dashboards with Streamlit, Power BI or Tableau.
11 · Writing
All posts →
Notes on data engineering & AI.
dbt vs DuckDB: What Each One Does and How They Fit Together
dbt and DuckDB are not competing tools. dbt organizes and tests SQL transformations, and DuckDB is a database that can run them. Here is how they fit.
Read more →
Marketing Data Pipeline: How to Combine Campaign Data Into One Source
A marketing data pipeline pulls ad, email and analytics exports into one clean source. Here are the steps, the pitfalls, and how to keep it reliable.
Read more →
Text Embeddings Explained: How Text Becomes Numbers
A text embedding turns text into numbers so similar meanings sit close together. Here is how embeddings, cosine similarity and vector search work.
Read more →
12 · FAQ
Good questions.
What kind of projects do you take on?
I work on data pipelines, warehouse modeling, ETL/ELT, and applied ML/AI projects — from a single dashboard to a full production pipeline.
Are you available for freelance or full-time roles?
Yes — update this answer with your current availability.
What tools do you use most?
Python, SQL, dbt, Airflow, Docker, and cloud platforms including AWS, Azure and GCP, alongside scikit-learn/TensorFlow/PyTorch for ML work.
13 · Contact
Have a data problem worth solving?
Send a message and I'll get back to you soon — or reach out directly: