Machine Learning Engineer Intern (TikTok BRIC Account Security) - 2027 Start (PhD)

TikTok is a world-leading short-video and live streaming platform serving hundreds of millions of users globally. By joining the BRIC (Business Risk Integrity Control) team, you will work in one of the industry's most challenging risk environments, where massive scale, high concurrency, evolving abuse patterns and global adversarial ecosystems continuously reshape the landscape.

You will build the next generation of intelligent, data-driven risk defense systems, combining strategy, product thinking and AI to safeguard the health of the global content ecosystem and continuously raise the industry's standard for risk governance.

We are looking for talented individuals to join us for an internship.

PhD internships at Our Company provide students with the opportunity to actively contribute to our products and research, as well as to the organization's future plans and emerging technologies.

Our dynamic internship experience blends hands-on learning, enriching community-building and professional development events, and collaboration with industry experts.

Applications will be reviewed on a rolling basis, so we encourage you to apply early. Please clearly state your availability in your resume (Start date, End date).

Responsibilities - Leverage algorithms and cutting-edge AI technologies/tools to address account security-related risk issues across TikTok and other overseas business lines, including scenarios such as social, live streaming, e-commerce, local services, and payment. - Tackle specific account security challenges, including but not limited to: fraudulent bulk registration, account trading, malicious account farming, account theft, and ticket hijacking. - Build features and perform representation learning based on multi-source data (e.g., account behavior, ecosystem behavior, device fingerprints, graph relationships, text and image content, etc.) to enhance both real-time and offline perception and detection capabilities; conduct model evaluation and online experimentation, with close attention to stability, drift monitoring, and interpretability. - Explore and develop a risk-control Agentic AI architecture, including the design and optimization of Skills, long-chain task orchestration, and multi-agent collaborative problem-solving, to improve the efficiency of risk identification and incident resolution.