ML Engineer, AI Risk & Integrity Platform

TikTok USDS Joint Venture; Seattle (WA); On-site; USD 130,000 - 246,000; Full time

Job summary

TikTok USDS Joint Venture LLC is seeking a skilled AI Platform risk engineer to own the algorithmic architecture for US risk & integrity across accounts, content safety, and financial risk, using multimodal data and scalable ML.

This role emphasizes building high-precision risk models, integrating Generative AI, and defending against large-scale adversarial threats, with cross-cultural collaboration to ensure a secure, fair ecosystem.

Qualifications

• Bachelor's degree or higher in Computer Science, Mathematics, Statistics, or a related field.
• Solid foundation in Machine Learning; proficient in applying Transformer and GNN architectures to solve large-scale integrity challenges with social graph and behavior sequence data. Experience designing model evaluation systems that balance technical performance with product goals.
• Strong engineering and coding skills. Proficient in at least one language among Python, C++, or Go; familiar with distributed computing (e.g., Spark, Flink) and deep learning frameworks (e.g., PyTorch).
• A passion for building world-class risk infrastructure and the ability to communicate effectively in a global, cross-cultural environment.

Responsibilities

• Global Ecosystem Governance: Lead the algorithmic architecture and governance for TikTok US across key domains, including account integrity, incentive abuse, content safety, and financial risk, ensuring a fair and secure ecosystem for a billion-user community.
• Universal Representation Modeling: Build high-precision, risk representation models leveraging massive heterogeneous data (video, live streams, audio, behavior sequences, and social graphs) to enable cross-scenario risk perception.
• Dynamic Adversarial Defense: Research and counter global adversarial threats (e.g., large-scale automated attacks, AIGC harmful content). Architect self-evolving defense systems that maintain robustness and resilience against rapid tactic shifts and data drift.
• Intelligent Decision‑making: Drive the integration of Generative AI and Multimodal technologies into the risk lifecycle. Leverage LLMs and deep learning models to solve complex adjudication and interpretability challenges, balancing precision with automated, large-scale enforcement.

Skills

Transformer architectures

Graph Neural Networks (GNN)

Python

C++

Go

Spark

Flink

PyTorch

Machine Learning

risk infrastructure

Education

Bachelor's degree or higher in Computer Science, Mathematics, Statistics, or a related field

Tools

PyTorch

Spark

Flink

Job description

TikTok USDS Joint Venture LLC is seeking a skilled AI Platform risk engineer to own the algorithmic architecture for US risk & integrity across accounts, content safety, and financial risk, using multimodal data and scalable ML.

This role emphasizes building high-precision risk models, integrating Generative AI, and defending against large-scale adversarial threats, with cross-cultural collaboration to ensure a secure, fair ecosystem.