🧠 AI/ML specialist with 8+ years deploying fraud detection, NLP, and churn models in real-world systems<br>⚡ Delivered scalable ML pipelines and MLOps solutions for BNP Paribas, ZingHR, and Ambrella AI<br>🔌 Integrated custom models via APIs, enabling fast, stable production deployments<br>📊 Strong data engineering background — expert in Python, SQL, Apache Spark, and real-time processing<br>☁️ Deep experience with cloud platforms (AWS, GCP, Azure) and end-to-end architecture<br>🎓 Data science instructor and Master’s student, focused on turning advanced analytics into business results<br>
Designed and delivered comprehensive lectures on key topics like data pipelines, ETL processes, and data warehousing.
Crafted and evaluated assignments and exams to measure students' understanding, developed real-time simulations for practical experience, and collaborated with fellow instructors to refine the curriculum, ensuring alignment with industry standards.
Educated professionals in becoming data engineers, focusing on SQL, Python, Spark, Airflow, and data warehousing concepts.
Used Python, Apache Spark, SQL, and Apache Airflow in the instructional content and practical exercises.
Led the design, development and optimization of streaming and batch data pipelines, advanced data monitoring, and data warehousing solutions.
Deployed robust AI/ML models into production ensuring data integrity and conducted comprehensive data analysis.
Architected an AI tool for fraud detection that identifies fraudulent credit card transactions, and implemented into the existing tech stack to enhance online secuirty.
Engineered a sophisticated data pipeline to streamline data processing and analysis, supporting various data-driven initiatives.
Architected and implemented scalable data pipelines and developed and maintained ETL processes for AI models, integrating them into existing applications via APis, and ensuring high performance and accuracy of data systems.
Led the development of an NLP-based entity resolution and matching system using BERT and Random Forest models integrated within a data pipeline, deploying the solution using Apache Spark in a production environment using Apache Spark.
Collaborated with the DevOps team to facilitate smooth deployment of models to production environments.
Developed high-performance algorithms and data pipelines for text processing using Python and Rust.
Directed a project on network analysis of social media for personalized ads incorporating GPT-2-based text generation systems, enhancing targeted advertising strategies.
Designed and implemented large-scale data transformation solutions using AWS and MongoDB and deployed advanced models to production, optimizing them for efficiency and accuracy.
