Data Engineer & MLOps Enthusiast
Passionate about building scalable, reliable, and production-ready data systems, I specialize in designing end-to-end data platforms combining Data Engineering, Machine Learning, and MLOps.
I have worked on advanced projects such as a Scoring & Fraud Detection Platform (MLOps) integrating real-time streaming, ML models, and compliance automation (KYC/AML), as well as end-to-end ELT pipelines and Big Data analytics systems.
💡 My core expertise includes:
- Real-time data pipelines (Apache Kafka, Spark, Airflow)
- MLOps & model lifecycle (MLflow, Docker, Kubernetes)
- Data quality & governance (Soda Core, monitoring, validation)
- Scalable architectures (batch & streaming)
- Scoring & Fraud Detection Platform (MLOps)
- Real-time pipelines with Kafka + Spark Streaming
- Advanced monitoring & observability (Grafana, Prometheus)
- Advanced MLOps (MLflow, Kubeflow, Feature Store)
- Cloud Data Engineering (GCP / BigQuery optimization)
- LLM integration in data platforms
- Data Engineering & MLOps projects
- Open-source data platforms & analytics tools
- Advanced orchestration with Apache Airflow
- Distributed system design & optimization
- Data pipelines (Batch & Streaming)
- MLOps & ML lifecycle
- Data modeling & architecture
- Fraud detection & scoring systems
- Database Design & Optimization : Relational & NoSQL schema design, query tuning, indexing, normalization
- ETL & Data Processing : Apache Spark, Kafka, Airflow, data cleaning, transformation, pipeline orchestration
- Machine Learning & AI : NLP models, clustering, classification, predictive analytics (Random Forest, Logistic Regression)
- Automation & DevOps for Data : Kubernetes, Docker, CI/CD for scalable deployments
- Data Visualization & BI : Tableau, Power BI, dashboard creation, KPI monitoring
| speciality | Technologies |
|---|---|
| Data Engineering | |
| Data Science | |
| Others (Dev & Frameworks) |


