E-commerce ML Engineer: Risk Detection & Graph Learning

TikTok; Singapore; On-site; SGD 120,000 - 190,000; Full time

Job summary

TikTok is seeking a PhD-qualified researcher to advance AI-driven risk detection for its e-commerce ecosystem. You will mine and model data to identify high-risk merchants, products, and creators, and build scalable ML solutions that improve product experience and governance across live streaming, video, and related domains.

The role emphasizes collaboration across teams, cutting-edge research, and production-ready models that scale to large datasets and diverse content, with opportunities for

Qualifications

• PhD candidate or recent PhD in a technical field related to software development or computer science.
• Solid coding skills and familiarity with deep learning/graph learning frameworks.

Responsibilities

• Mine, identify, and predict risks and low-quality merchants, products, and creators in e-commerce using algorithms.
• Build data models to support ecosystem health and business operations.
• Contribute to data for entities like live streaming, products, merchants, and creators with large-scale models.
• Help build a large-scale graph storage and learning platform to improve governance within the community.
• Explore and implement cutting-edge ML/graph/sequence learning technologies in production.

Skills

PyTorch

TensorFlow

Graph neural networks

Machine learning

Deep learning frameworks

Data modeling

Python

NumPy/Pandas

Big data tools

Education

PhD in Software Development/Computer Science/Computer Engineering

Tools

DGL

pyg

scikit-learn

Hive

Spark

Hadoop

Job description

TikTok is seeking a PhD-qualified researcher to advance AI-driven risk detection for its e-commerce ecosystem. You will mine and model data to identify high-risk merchants, products, and creators, and build scalable ML solutions that improve product experience and governance across live streaming, video, and related domains.

The role emphasizes collaboration across teams, cutting-edge research, and production-ready models that scale to large datasets and diverse content, with opportunities for