Hanoi, Hanoi, Vietnam
Senior data engineer and build Data Warehouse model with logical thinking ability and background in Data Modelling, Data Warehouse and Data Lake. Passionate about building model Data warehouse, Cloud Data and Bigdata.
Machine Learning Team Lead Data Pipeline Development: Designed and managed scalable data pipelines on Spark, Hadoop, and Airflow, integrating data from 10+ heterogeneous sources stored on on-prem S3; optimized ETL flows with YARN-based orchestration, reducing model training latency by 30%. Model Deployment: Deployed 15+ ML models from research to production; containerized and exposed models as APIs/microservices, enabling seamless integration with enterprise systems and reducing deployment time from weeks to days. MLOps & Metadata Management: Implemented model monitoring, experiment tracking, and versioning with MLflow; automated retraining pipelines to handle data drift; leveraged OpenMetadata for data lineage and governance across ML pipelines. Team Leadership: Led and mentored a cross-functional ML team, delivering production-ready ML solutions aligned with business requirements while ensuring best practices in data governance and scalable architecture.
- Collaborate with developers to build APIs that aggregate data from stock data sources. - Control the quality of the source data and building data control rules. - Build Data mart to synthesize data for stock data analysis model - Design ETL Data Flow with SSIS - Design local website to provide data dictionary about stock data - Design Data flow for real-time derivatives stock data - Operation data server daily
DWH project: + Work closely with IBM foreign experts about IBM Banking IBM Banking Model + Analyze and clarify business requirements + Design data model based on IBM's model (Modeling) - Atomic data decomposition (SoR) - Build in-depth Datamarts for each business + Participate in the development of a set of general principles on data design, operation and use at VPbank
Circular 11 project: + Collect how to determine the reporting criteria of the business + Develop data models on existing Datamart + Report development on BI tools (Cognos 11) + Design jobs to automatically run reports on BI tools (Cognos 11) + Manage and operate reporting and data systems - BAU job + Build, develop and operate data related requirements such as building datamart, job, toolreconcile, ... serve units that use data to make reports. + Data support ensures data is always available, accurate and timely. + Other assigned tasks from teamlead and manager. + Participate in internal training sessions, professional training sessions organized by the bank.
Datamart SME: + Develop job/code according to details mapping + Work closely with BU to clarify logic + Operate job in SSIS