Ming Liu, AI Engineer and Developer in Singapore, Singapore
Ming Liu

AI Engineer and Developer in Singapore, Singapore

Member since May 4, 2021
Ming is a machine learning engineer specializing in recommender and anti-fraud systems. He has been working in data science and AI for the past four years, including building and improving the recommender system for Shopee and TikTok, which have hundreds of millions of users and items. Ming's industry experience is backed by a master's degree in computer science.
Ming is now available for hire

Portfolio

  • TikTok
    C++, Python, Recommendation Systems, Neural Networks
  • Shopee
    Algorithms, Anti-fraud, Graph Databases, Apache Airflow, PySpark, eCommerce
  • Shopee
    Python, Recommendation Systems, Graph Databases, Neural Networks...

Experience

Location

Singapore, Singapore

Availability

Part-time

Preferred Environment

Linux, PySpark, Python, Keras, TensorFlow, Docker

The most amazing...

...system I've developed was for TikTok, and it's popularity is due, in large part, to the successful recommender system I built.

Employment

  • Machine Learning Engineer

    2021 - PRESENT
    TikTok
    • Improved TikTok's live streaming recommendation system by adding multiple retrieval and recall queues.
    • Improved TikTok's live streaming recommendation system by using more complex neural networks and adding more concrete objectives and targets for the system.
    • Increased TikTok's overall live-streaming revenue by applying multiple revenue strategies, implementing those strategies in the system, and conducting A/B tests.
    Technologies: C++, Python, Recommendation Systems, Neural Networks
  • Senior Data Scientist

    2019 - 2020
    Shopee
    • Led a team of five (plus two interns) to build and refactor a unique user identification system, which included setting up a graph database and building a data pipeline and business engine.
    • Collaborated with team members to build an interactive data dashboard for managers and other colleagues to explore the user-user relationship.
    • Assisted team members with improving JanusGraph, an open-source tool, according to business requirements.
    Technologies: Algorithms, Anti-fraud, Graph Databases, Apache Airflow, PySpark, eCommerce
  • Data Scientist

    2018 - 2019
    Shopee
    • Increased the click-through rate on the homepage recommender system by 50% by using deep neural networks.
    • Increased the conversion rate on the shopping cart page by around 20% by using online learning to build a new module called "You may also like."
    • Created graph database clusters and used the database to store buyer-seller relationships.
    Technologies: Python, Recommendation Systems, Graph Databases, Neural Networks, Deep Neural Networks, Machine Learning, eCommerce
  • Machine Learning Engineer

    2017 - 2017
    XRVision
    • Built object detections for CCTV cameras for buildings, factories, and roads, with more than 70% accuracy.
    • Developed image classification models for the company's core product that has the general ability to recognize gender, facial hair, eyeglasses, and other features, with an overall accuracy of 90%.
    • Built facial recognition models for several companies' check-in systems.
    Technologies: Python, C++, Computer Vision, Object Detection, Facial Recognition, Machine Learning, Anti-fraud

Experience

  • Enhanced Recommendation System for eCommerce Website

    As a machine learning engineer, I collaborated with a data engineer and a software engineer to enhance the recommendation system of the Shopee eCommerce website. By training neural networks on customer browsing and purchasing data, I used the deep learning method to improve the recommender system and improved the click-through rate by 50%+ compared to the previous baseline.

  • Object Detection for CCTV Cameras

    An object detection neural network that allows CCTV cameras to detect different types of cars and people. It also applies facial recognition if the faces are big enough on the screen. At 10 frames per second, this function works in near real time.

  • Refactored Unique User Identification System for eCommerce Website

    Led a team of five (plus two interns) to build and refactor a unique user identification system. This included setting up a graph database and building an interactive query graph dashboard, a data pipeline, and a business engine.

    This project helps the company understand which users are highly likely to be fraudsters who created multiple accounts to get benefits. By using Go to replace Python, the system performance improved by 80% in terms of increased speed and decreased memory.

Skills

  • Other

    Recommendation Systems, Machine Learning, Deep Learning, Deep Neural Networks, Data Analysis, Data Visualization, Data Structures, Algorithms, Neural Networks, eCommerce, Computer Vision, Anti-fraud, AWS, Object Detection, Facial Recognition, Team Leadership, System Design
  • Languages

    Python, SQL, Go, C++
  • Frameworks

    Spark, Flask
  • Libraries/APIs

    PySpark, TensorFlow, Keras, OpenCV
  • Platforms

    Linux, Docker
  • Storage

    Graph Databases, Neo4j, Elasticsearch
  • Tools

    Apache Airflow

Education

  • Master's Degree in Computer Science
    2017 - 2018
    National University of Singapore - Singpore
  • Bachelor's Degree in Information Technology
    2012 - 2016
    Southeast University - China

To view more profiles

Join Toptal
Share it with others