Van Nguyen

AI Engineer and Data Engineer with experience in building data pipelines, AI solutions, and cross-functional leadership. Passionate about democratizing education through AI and applying data science to agricultural life sciences.

- Designed and executed data pipelines to retire the legacy MSSQL warehouse and stand up SAP Datasphere as the new SQL‑layer platform.
- Built connectivity between SAP ECC/S4, Salesforce, Tableau, Power BI, SAP BAS Python IDE, and Datasphere, resolving authentication, driver, and network issues.
- Migrated Python ETL jobs from an on‑prem Windows server to containerized runners, improving maintaina

- Owned and enhanced the Python alert-processing pipeline to reliably handle multiple email/alert formats and variations from different sources.
- Led data cleaning and standardization, defining a consistent input schema/format for entities that need to be alerted (customers/projects/assets) to keep downstream processing stable.
- Collaborated closely with the Java team to understand data returned

- Used APIs from OpenAI GPT‑4o, Gemini Pro, Mistral Large, and Llama 3 in Jupyter notebooks to solve end‑to‑end data problems.
- Implemented CV–JD relevance scoring, résumé parsing, competency analytics, and personalized interview‑question generation for recruiters.
- Built entity‑resolution services that (a) match invoices to purchase orders by item, price, tax, and quantity, and (b) reconcile re

Through a consultation contract, I dedicated a few hours a week to assist ITviec with the following responsibilities:

- Worked directly under the CEO to provide strategic data management insights.
- Consulted on structuring data flow from production to reporting, ensuring efficient and seamless data processing.
- Advised on building and scaling data and AI teams to meet organizational needs.
- Pr

- Identify new business opportunities by examining sales and marketing reports.
- Work closely with Sales Director, Marketing Director, and Project Manager to leverage data insights for growth strategies.
- Collaborate with the Product, Data Engineer, and Data Scientist team to collectively build and implement innovative new features or identify and solve problems.
- Support new feature releases t

- Allocating loan contract to collection department and call center using Python and PL/SQL Oracle.
- Cleaning and preprocessing credit card data to make ad hoc reports.
- Classification of debt groups by clustering algorithms (k-mean)
- Cleaning and preprocessing data, then feeding data to check the correlation between data fields. Using finding from this to guide the collection center.
- Write E

- Builds and defines the application tracking report system for the Staffing Services.
- Collaborate with the Research team to conduct in-depth market analyses of recruitment trends, and utilize the gathered insights to create detailed statistical reports, including competitor pricing and a comprehensive market overview.
- Use Python to clean HR data (resume, portfolio, ID, salary, day-offs, SHUI,

- Installation, maintenance, configuration, and repair software.
- Be responsible for daily support system management, including computer and AV systems, CRM, ERP, VR/AR Education Kit, 3D printer,... in the American Center.
- Working with the MakerSpace activities.
- Assisting with the American Center and EducationUSA design projects.
- Report weekly using Excel and Canva.
- Use python to automate