"Business Risk Integrated Control (BRIC) is a global team protecting ByteDance users, platform health, and the authenticity of community and business ecosystems. We build the risk control algorithms, AI technologies, platforms, and infrastructure behind that work, across products including TikTok, CapCut, Lemon8, and Lark.
Our work spans account and content integrity, and safety across advertising and e-commerce. We apply machine learning across areas such as graph learning, anomaly detection, and multimodal models to understand users, content, behavior, and the relationships between them. The challenge is recognizing genuine activity accurately, so the people using our products never notice the systems working.
You will shape the trust, safety, and sustainable growth of ByteDance's global platforms, applying advanced AI to some of the hardest real-world problems in the field."
Program Intern (Conversion-Oriented): for graduating students who are looking for full-time conversion as the primary objective.
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 tackle account security risks across TikTok and other overseas offline businesses, including social, live streaming, local services, e-commerce, payment and other scenarios.
- Address account security issues including but not limited to bulk fake account, account trading, malicious farming, account takeover, ticket hijacking, etc.
- Build features and representation learning based on multi-source data (account behavior, ecosystem behavior, device, graph relationships, text & image content, etc.). Improve real-time and offline risk perception and detection capabilities of models. Conduct model evaluation and online experiments, with close attention to stability, drift monitoring and model interpretability.
- Research and build the architecture of risk-control Agentic AI; develop and optimize Skills, long-chain task orchestration and multi-agent collaboration mechanisms to improve the efficiency of risk discovery and resolution.
Key internship research topics:
- Research and build pre-trained models tailored for account security scenarios, and continuously iterate post-training via SFT, RL and related techniques.
- Research and build long behavioral sequence models for account security, and apply them to risk identification and detection.
Minimum Qualifications:
- Currently pursuing a PhD in Computer Science or a related discipline.
- Solid engineering experience with LLM / Agent systems, proficient in mainstream agent tooling.
- Strong engineering capability, proficient in Python, SQL, and deep learning frameworks such as PyTorch/ TensorFlow.
Preferred Qualifications:
- Having high-quality publications at top conferences.
- Interest in high-adversarial risk control scenarios, and comfortable with technical challenges.
- Deep research experience in planning & reasoning, long task orchestration, memory & knowledge module, loop engineering, pre-training, RLHF, DPO, GRPO or related areas
By submitting an application for this role, you accept and agree to our global applicant privacy policy, which may be accessed here: https://careers.tiktok.com/legal/privacy