Ben Nguyen
Bilingual Data Scientist
About Me:
I am Ben, a freelance data scientist on UpWork with work experience such as the private sector, non-profits organizations, and the Canadian government related to technology. My core foci are artificial intelligence, software development, and cybersecurity. I am known for delivering data-driven solutions that directly influence and improve business strategies.
Toastmaster:
I am a member of Toastmasters International since 2019; I currently belong to the McGill University Toastmasters Club. My journey has taken me to virtual meetings across Ottawa, Montreal, Quebec, Washington D.C., Geneva, and Japan. Toastmaster has helped by developing a strong command of public speaking, leadership, and presentation. It has improved my clarity, my confidence, and my adaptability when presenting complex ideas to different audiences.
Projects:
WASDE REVENUE IN 2024:
Description:
The project uses PyTorch for AI applications to analyze WASDE revenue, achieving a model accuracy of 92%. Matplotlib creates histograms explaining export and import revenues. Pandas is used for data modeling and cleaning. LangChain prompts questions and answers for the LLM.
Chatbot Speech Recognition in Generative AI:
Description:
The goal of the project is to develop a chatbot using Google Speech technology to analyze information about the status of the Canadian economy in 2025 (Toronto Dominion Economic). The chatbot will utilize speech recognition to provide answers based on audio files from Toronto Dominion Economics, achieving a model accuracy of 92%.
Cybersecurity Risk Agentic AI:
Description:
The objective of the project is to develop an Agentic AI chatbot that focuses on the security risks associated with the technology. The chatbot utilizes LangGraph and Gemini to extract and analyze data from the document (Coaching AI Agents: Why Your Next Hire Security Hire Might Be An Algorithm), achieving a data extraction accuracy of 95%.
Alarm System Cybersecurity:
Description:
The C++ alarm system uses Agentic AI for real-time malware detection and neutralization, protecting users’ data. It employs a generative algorithm to identify threats early, resulting in an 30% increase in malware detection efficiency and boosting cybersecurity analysts’ efficiency in handling emerging risks.
DriveSmart: An Autonomous Mobility Solution:
Description:
This project delivers a Bluetooth-enabled application for secure, remote activation of an autonomous vehicle, verify the user with encrypted biometric data via PySyft (≥98% accuracy), detect faults using PyTorch (95% precision), show diagnostics on Plotly dashboard, and support multilingual reports in English, French, and Spanish via Agentic AI (≥97% accuracy).
Patient Electronic Health Record System:
Description:
The application utilises AI tools to assist in the clinical decision-making, employing Pandas for data extraction, processing over 1 million patient records, PyTorch for medication recommendations with an accuracy rate of 92%, and Agentic AI for bilingual reporting, generating reports in both English and French, supporting Canadian doctors in prescribing treatments suited to patient needs.
Tranquille Garden Text Application:
Description:
The application is developed with Python and features customizable fonts and adaptive color schemes to enhance readability. User data is secured using cryptographic methods, providing a high level of security. The integrated agentic AI supports document translation between English, French, and Spanish, reporting an accuracy rate of 98%.
AI Gateway Evolution: Moving from Requests to Results via Intent:
Description:
An intent-driven AI assistant supports daily tasks, detects prompt vulnerabilities, and delivers multilingual diagnostic reports via a Node.js-Python backend and PyTorch-powered intent engine, achieving ≥90% intent accuracy, ≤500ms latency, ≥60% daily engagement, and ≥95% translation precision.
Trade Transfer Workflow Optimizer:
Description:
The AI-powered portfolio assistant utilises secure RS256 encryption, sentiment overlays, and avatar-based insights to provide robust and reliable analysis. It delivers results in under two seconds with emotionally intelligent recommendations, achieving a minimum of 95% accuracy and 80% user engagement.
Continuous learning:
I am a lifelong learner with a passion for staying ahead of the curve. I have deepened my expertise in Cybersecurity through Coursera and Data Scientist: Natural Language Processing as part of Codecademy’s online program. My curiosity fuels a continuous pursuit of knowledge, especially in rapidly evolving fields such as Agentic AI, large language models (LLMs), generative AI, TensorFlow, Keras, and PyTorch. I strive not only to understand cutting-edge technology, but to apply it meaningfully and responsibly.
Work Experience:
Data Scientist (Freelance - UpWork)
February 2025 - Present:
-
Delivered AI, LLM, Generative AI, and Python solutions for a diverse clients projects.
-
Achieved a 20% reduction in project timelines through data modeling and data cleaning using Pandas for CSV files.
-
Built and optimized JavaScript based web applications for client-facing platforms, enhancing UI responsiveness.
-
Developed and debugged C++ software systems for client data processing needs, improving code efficiency by 20% and reducing by 30%.
Technical Expertise:
I have hands-on experience with various programming languages and technologies:
-
Languages: Python, SQL, JavaScript, C++, Node.js, TypeScript, Git, and GitHub.
-
AI & Machine Learning: LLMs, GenAI, TensorFlow, Keras, PyTorch, and Agentic AI.
I thrive on tackling complex challenges, driving innovation through collaboration, and pushing the limits of technology to create meaningful impact.
Education:
-
University of Ottawa:
-
Bachelor of General Social Science, 2011 - BACHELOR DEGREE.pdf
-
Codecademy:
-
Data Science: Natural Language Processing, 2024 - Data Scientist_Natural Language Processing_Codecademy.pdf
Volunteer:
OWASP Ottawa Chapter (Cybersecurity), Volunteer Staff: February 2025 - Present:
-
Greeted guests and introduced them to the chapter’s mission and events.
-
Assisted the leaders with event setup and logistics before the meetings.
-
Helped to create a welcoming environment for attendees and supported community engagement.
Video Content by Ben Nguyen on YouTube (Cybersecurity, AI, and Software):
Hackathon:
Hackathon 2025 (AI Tinkeres Ottawa - Build to Convert):
Our team has launched a website offering affordable meal plan subscriptions, supported by an Avatar Agentic AI that allows users to ask questions about the price of the meals in English or French.
Hackathon 2024 (NASA Space Apps Challenge_Hackalthon_2024.pdf):
I led a team to assess flood impacts across Canada by utilising ESRI mapping for geospatial visualisation, a modular backend for data processing, and a web-based frontend designed for stakeholder engagement.
Contact Information:
Email: nguyenben85@gmail.com