Hi, my name is
Mohamed Sabkhi
Your Friendly AI | Data Engineer
I leverage over a 2 years of expertise in driving End-to-End AI development, conducting insightful Data Analysis, implementing robust CI/CD pipelines, and optimizing cloud infrastructure for seamless operations.
Hi there! My name is Mohamed Sabkhi, I am a Data Scientist / Engineer, Alumnus of S.U.S.I Scholarship with University of Washington, and Ex Lead of Google Developers Student Clubs ENETCOM
With a passion for data science and a solid academic foundation, I have work experience in both data science and data engineering. I had the privilege of collaborating effectively with diverse individuals. I thrive on contributing to code projects within a team, harnessing collective creativity to solve complex data challenges.
Creativity and innovation drive my problem-solving approach, as I enjoy building products that positively impact society and automating repetitive tasks in my life.
July 2024 - Present
PUMA
Data Engineer
• Built EU-scale fraud detection system integrating multi-source retail data
• Leveraged product knowledge (e.g., high-demand sneakers) to identify theft patterns
• Recovered €87K in losses and caught 7 fraud cases through ML automation
• Developed real-time alerting and fraud cases management systems
• Technologies: Python, Pandas, bash, SQL, Databricks, PowerBI
May 2023 - November 2023
ADIDAS
Data Science Intern
• Contributed to developing a personal recommendation engine improving performance 3x while enhancing diversity of suggestions
• Optimized data pipelines processing terabytes of athlete performance and product data
• Transitioned system to production impacting millions of global users
• Implemented market-specific optimizations through behavioral pattern analysis
• Technologies: PySpark, Databricks, MLFlow, Python
Feb 2022 - May 2023
Cognifit
ML Contributor (Partnership)
• Developed open-source AI model to personalize cognitive training regimens
• Technologies: Python, PyTorch, Pandas
Jan 2022 - Apr 2022
Cognira
Data Engineer Intern
• Developed scalable data pipelines to support a cloud-based sports analytics platform
• Collaborated with cross-functional teams to streamline ETL workflows and automate data processing tasks
• Technologies: Python, Pandas, Databricks
Featured Project
Sentiment Analysis on Streaming Data using Azure Cloud
- The Sentiment Analysis on Streaming Data project harnesses Azure Cloud services to analyze real-time streaming data and extract sentiment insights. Through continuous processing, this project provides instant sentiment analysis results, enabling businesses to monitor public opinion, customer feedback, or social media sentiment in real time. Leveraging Azure's scalable infrastructure, the project offers a dynamic solution for organizations seeking timely and actionable sentiment intelligence from diverse streaming sources.
Python
Scala
Azure Cloud
Spark
SQL
Delta Lake
powerbi
Featured Project
Online Human Detector and Tracker
- Utilizing YOLOv5 and StrongSORT with OSNet. It consists of three notebooks for data scraping, model training, and inference on commercial videos. YOLOv5 is used for object detection, and the StrongSORT tracker is employed for tracking objects detected by YOLOv5.
Python
MLFlow
Git
Docker
Other Projects
Tap on a project to learn more!
Python
I am proficient in Python and have used it extensively for various applications, including backend development, data analysis, and machine learning projects. I am familiar with libraries like NumPy, Pandas, Matplotlib, and Scikit-learn.
- Python
- Java
- Git
- Github
- Kubernetes
- Docker
- Github Actions
- Jenkins
- Azure Cloud
- Google Cloud Platform
- AWS
- MongoDB
- Databricks
- Scikit-learn
- Pytorch
- TensorFlow
- Keras
- Pyspark
- Spark
- Pandas
- MLFlow
- Airflow
- NLP
- Linux
- SCRUM
- Kanban
- Unit Testing
- SQL
- Jenkins
- ETL
- R
- Scala
- DVC
- Gitlab
- Bitbucket
- MySQL
- PostgreSQL
- Time Series
- Kafka
- NoSQL
Master of Science in Data Science
National Engineering School of Electronics and Telecommunications of Sfax
- Cloud Computing
- Data Visualization
- Data Processing at Scale
- Natural Language Processing
- Data Mining
- Programming Languages: Scala, Python, Java, C++, SQL
Courses
2020 - 2023
GPA: 3.9
Study of the U.S. Institutes for Student Leaders
University of Washington
- Effect of Information Technology on Seattle
- Extracurricular cultural and community activities
Courses
2022 - 2022
GPA: 4
Pre-Engineering Cycle
Preparatory Institue for Engineering Studies of Monastir
- Applied Mathematics
- Alegbra
- Classical & Quantum Physics
- Mechanics
- Data Analysis
Courses
2018 - 2020
GPA: 3.7
If you would like to work together or discuss an opportunity for work, please use the form or send me an email on medsabkhi@gmail.com