Data Scientist Engineering
Resume:
Cương Nguyễn
Duy
Data engineering
cuongnd.ba12-
***@**.****.***.**
https://www.facebook.com/pro
file.php?id=100************
Cau Giay District, Ha Noi
python,java,c++,PHP
Framwork: Flask, Django,Laravel
Crawl data: Selenium,
Beautifulsoup
Database: MySql, MongoDB,
Elasticsearch,PostgreSQL
Image processing: OpenCV, Yolo
V9, DeepFace, InsightFace
Rest ful Api with Postman
Package : Docker
Nature language processing: LLMs,
T5, Ner
Process data: Numpy,
Pandas,Spark
Office informatics: Excel, Word
My hobbies is: Sport, food and
playing a game
Want to become an official Data Analysist of a company and stay for a long time. INTERN DATA SCIENTIST - AI 1/5/2024 - 5/9/2024
FPT IS
Project: Build system recommend job for ITviec.
Teamsize Ai size: 7 personses.
ask Description:
Data Crawling (excluding ITViec page):
Utilize the Scrapy framework along with HTTP requests to crawl data. Target 20,000 CV PDFs for data extraction.
Develop a tool to convert the raw data into JSON format and ingest it into Elasticsearch.
Implement an API using OpenAI to interact with the data in Elasticsearch. Research Directions:
Direction 1: Convert PDF files into images, apply labels, and then extract data using YOLOv9 combined with Roboflow.
Direction 2: Convert PDFs to text and then apply natural language processing
(NLP) techniques to clean the data.
Image Extraction and Deduplication:
Extract images from CVs and utilize DeepFace to compare images, identifying and removing CVs with duplicate profile pictures.
Job Clustering and Recommendation:
Implement an API for job clustering based on the data. Use the API to recommend jobs when an external CV is uploaded AI engineer 9/10/2024 - 28/12/2024
FPT software
Project: Build Chatbot support employees internal in company. Team Ai size: 13 persones.
Task Description:
Data Dev:
Join in project design Chatbot system.
Write the functions process data input from user.
Processing input dataset for train:
Train model reinforcement learning with T5 for terminology ( Japanese - Vietnamese).
Backend :
FastAPI build process translate Japonese - Vietnamese Thread. Add more above project:
Research LANGCHAIN (LLMs-RAG)
+ Process data: Extract information from a lot of form (Pdf, Images, excel ) then save data from FAISS
+ Train with model Langchain ( call api from hugging face, openai )
+ Check accuracy, lossfunction
Data analysist + DEV php ( Freelance at night) 10/02/2025 - Now Communication ATT company
Data analysist
Phase 1: is to collect and search for data based on available lat, lon (using Nominatim API + OpenstreetMap)
Phase 2: is from collecting data, cleaning data
Phase 3: divide data into mongoDB and Mysql depending on purpose Techlead Web dev
Create a job management search function for employees on the website https://retailmedia.adtrue.dev.vn/
Make recommendation function for customers using lat, lon and build chatbot based on available data for website
Data analysist 10/02/2025 - Now
SMEDICARE Healthcare System Joint Stock Company
Responsible for troubleshooting and resolving Python-related errors during data extraction from PostgreSQL databases and syncing to Google Sheets via API. Handled data integrity issues such as customer mapping errors and data loss, ensuring accuracy and consistency across systems.
Developed interactive dashboards and visual reports in Google Sheets to support departments like Customer Care, Insurance, and Internal Teams. Proficient in advanced Excel functions including INDEX/MATCH, QUERY, ARRAYFORMULA, and other data processing techniques. Managed and maintained a large-scale healthcare data system comprising over 900 relational tables, covering patient records, treatment history, insurance claims, and customer interactions.
Collaborated with multiple departments to calculate performance metrics and generate automated reports based on department-specific mechanisms. ADD Information: Applied machine learning models to forecast departmental KPIs over specific time periods, enabling data-driven planning and performance optimization.
Information and communication of technology 2021 - Now University of science and technology of Hanoi
2021 Second prize in physics in Thai Binh province. B2 English (21/06/2021) Name certificate: Ielts (6.0) B1 French Name certificate: DELF
-
backend DEv
Web selling milk 15/2/2024 - 16/3/2024
Shop
5 members
Describe project:
• Online milk selling websites not only bring convenience and better experience to consumers, but also help businesses optimize business operations, reach My more task in customers project: and enhance competitiveness in the market. 1User management Registration and login:
• Handles new account registration and login for users. Manage user authentication via email or phone number.
• User information management: Store and update users' personal information, including name, address, phone number, and payment information.
• Authentication and authorization: Ensure users have the correct access rights to parts of the system. Manage user access, distinguishing between regular users, administrators, and support staff.
2. Product management
• Product CRUD: Create, read, update, and delete product information. Manage a list of milk types, brands, product descriptions, prices and inventory quantities.
• Classification and tagging: Classify products according to criteria such as milk type, brand, age of use, etc.
3. Order management
• Order processing: Receive, confirm, and track orders from order placement to successful delivery.
• Track order status: Update order status such as confirmed, processing, shipping, and delivered.
• Cart management: Store and manage user's cart information, including selected products, quantities, and prices. © topcv.vn
Contact this candidate