Mohamed Nijadi

Currently on a long-term assignment (9 months+) for a major AdTech player, I assist companies in optimizing their data pipelines and deploying high-performance Machine Learning models.

MyFull Stack Dataprofile allows me to work across the entire value chain: from cloud infrastructure to modeling.

💡 **Recent Key Achievement**: Optimization of a critical inference pipeline on a massive dataset (AdTech):

**-> Result**: Reduction of execution time from 8 hours to 2 hours and tripling of simultaneous processing capacity.

🚀 **My Areas of Expertise**:

1.**Data Engineering & Cloud (AWS / Databricks)**

Building and optimizing ETL pipelines (Spark, Python).

Migration of infrastructures (e.g., AWS Sagemaker/Athena to Databricks).

Management of databases and Data Warehousing (Redshift, S3, Glue).

Certification: AWS Data Engineer Associate.

Implementation of Machine Learning algorithms (Scikit-learn, MLFlow).

Processing and Analysis of complex data (Spark, Polars).

Feature Engineering / Feature selection.

Statistical analysis and data visualization

Implementation of a data quality & data cleaning strategy.

Design of dashboards adhering to best practices (Power BI / Tableau).

**🛠 Technical Stack**:

**Languages**: Python (Polars, Pandas, Scikit-learn, Airflow), SQL.

**Big Data**: Spark, Databricks.

**AWS Cloud**: Athena, Sagemaker, Glue, Redshift, S3, Lambda.

**Viz**: PowerBI, QuickSight.

Accustomed to remote work with demanding technical teams, I am autonomous and results-oriented.

Feel free to contact me to discuss your Data projects.