Terrance Duc - Senior Al Engineer

Terrance Duc

4.9

Select me!

Terrance is available for hire

Hire Now

Terrance Duc

4.9

Gender

Male

Main expertise

AI Data Scientists Data Machine Learning Deep Learning NLP PyTorch TensorFlow Python Big Data Architects Data Analysts Database

Introduction

Terrance Duc is an accomplished Data Scientist and AI Engineer with over six years of experience in extracting, analyzing, and interpreting large datasets from diverse sources. Utilizing algorithmic approaches, data mining, artificial intelligence, machine learning, and statistical tools, he makes data accessible and valuable to businesses. Terrance is passionate about delivering insights through analytical functions and data retrieval methods. He is adept at managing data from multiple streams and excels at synthesizing quantitative information while effectively interacting with colleagues and clients.

Project list

AI-Driven Retail Automation System

Develop and implement an advanced computer vision software solution tailored for the grocery retail industry. This system harnesses AI-powered product identification technology to minimize checkout errors, decrease plastic packaging waste, and boost operational efficiency. By enhancing the shopping experience, this project aims to provide a more rapid, convenient, and sustainable retail environment for customers while fostering growth for grocery businesses.

Develop and train generative AI models using frameworks such as TensorFlow and PyTorch. Implement various NLP tasks, including text classification, sentiment analysis, named entity recognition, and language translation, utilizing generative AI models. Continuously monitor and optimize generative AI model performance to ensure high accuracy, efficiency, and scalability. Develop and implement data pipelines to collect, process, and analyze data from various sources.

Technologies: Python, TensorFlow, PyTorch, Generative Adversarial Networks, GCP

FLYER

FLYER is a pioneering virtual interactive English testing platform designed specifically for kids, focusing on high-quality assessments.

Study existing database, data flow, business. Clean and transform, manipulating data for analysis and visualization. Create Google Data Studio dashboards for major performance metrics, based on customer expectation. Design, develop, and optimize automatic scoring for writing tests. Design, develop, and optimize automatic scoring for speaking tests. Design, develop, and optimize automatic generation of images and quizzes to use as learning content.

Technologies: Azure, PostgreSQL, MongoDB, Python, Google Data Studio, Kafka, Spark (ML), TensorFlow, Scikit-learn, LLM, ChatGPT, Supervised Learning, Reinforcement Learning, Stable Diffusion, GAN

Healthcare Services Optimization Platform

The project involved working with one of the largest healthcare services groups in Asia. The group's offerings include world-class distribution, commercial solutions, patient care, clinic reach, data analytics, pharmacy channel, and payor services, aiming to support the growing healthcare needs in the region.

Study existing database, data flow, and business processes. Clean, transform, and manipulate data for analysis and visualization. Design, develop, and optimize a machine learning classification model for categorizing merchant groups. Design, develop, and optimize an automatic scoring system for writing tests. Design, develop, and optimize a machine learning recommendation system for inventory optimization.

Technologies: PowerBI, Postgres, HANA, Azure Synapse, DAX, DAX Studio

INVETO

INVETO is an online data analysis platform utilizing AI for investors. It offers products including cryptocurrencies, securities, and real estate. The platform integrates AI and ML algorithms to suggest buying and selling options, and provides information on product trends and price history.

Study existing database, data flow, and business. Clean, transform, and manipulate data for analysis and visualization. Apply big data solutions to solve current business problems. Design, develop, and optimize a machine learning recommendation system for buy/sell decisions. Design, develop, and optimize an ML Stock News Analyst and summary using ChatGPT.

Technologies: NodeJS, PostgreSQL, TensorFlow, Kafka, AWS, Kubernetes, Docker, Scikit-learn, Python, Pytorch, Supervised Learning, ChatGPT

AlSuviet

AlSuviet serves as an insightful advisor, facilitating user access to historical knowledge from reputable sources through chatbot interactions. Additionally, by digitizing documents, the platform aids in the preservation and archiving of knowledge for future generations.

Study existing database, data flow, business. Clean and transform data, manipulating it for analysis and visualization. Design, develop, and optimize an AI Chatbot using local knowledge with Google PaLM v2. Analyze and implement training algorithms. Design, develop, and optimize a machine learning classification model to detect inappropriate messages and questions.

Technologies: AWS, PostgreSQL, Python, Apache Superset, Hadoop, TensorFlow, PyTorch, Scikit-learn, Supervised Learning

Gaspol Project

An innovative Automotive, Sport, and Digital Media platform designed to cater to your daily mobility needs.

Study existing database and data flow. Clean and transform data for analytics. Create Google Data Studio/Superset dashboards to measure key performance metrics as per customer expectations. Migrate data from the legacy system to the new one. Fix various data bugs.

Technologies: PostgreSQL, Java, Google Data Studio, Apache Superset

VECA Project

A startup in Vietnam that offers a matching system for users and dealers to efficiently collect waste.

Study existing database and data flow. Clean and transform data for analytics. Create Google Data Studio views for major performance metrics, based on customer expectations.

Technologies: MySQL, Google Data Studio

Statistical Analysis of Asphalt Pavement Testing

This project focuses on the statistical analysis of mechanical measurements collected during a comprehensive full-scale test of reinforced asphalt pavement. The aim is to enhance the understanding of the test results to better evaluate the performance of the pavement.

Statistical analysis of mechanical measurements during a full-scale test of reinforced asphalt pavement using Python. Collect data and design a dataset highlighting key characteristics of a pavement structure. Study and interpret the large dataset using Panel analysis, adhering to the Cross Industry Standard Process for Data Mining (CRISP-DM) methodology.

Technologies: PostgreSQL, Python, Apache Superset, Azure

Taxi Trip Duration Prediction and Pavement Performance Analysis

This project aimed at predicting the duration of taxi trips in New York City using data mining techniques. Additionally, it involved a statistical analysis of mechanical measurements during a full-scale test of reinforced asphalt pavement. The analysis helps in understanding the test results better and in evaluating pavement performances comprehensively.

Predict duration of taxi trips in New York City using Java and R. Solve data mining problems by applying models like linear regression and artificial neural networks. Follow the CRISP-DM methodology in executing the project tasks.

Technologies: PostgreSQL, Java, Google Data Studio, Apache Superset

Social Network User Profiling and Influencer Detection

The project aims to address the challenge of users having incomplete profiles in a social network. The goal is to develop methods to fill in missing information and identify key influencers, who are users with extensive connections within the network.

The illusion of hidden personal data using Python. Fill incomplete profiles and identify influencers in a network using community detection methods such as hierarchical clustering, Louvain method, and simulated annealing, following the CRISP-DM methodology.

Technologies: Azure, PostgreSQL, Python, Apache Superset

Project list

Education

Expertise