The E-Commerce Risk Control (ECRC) team is responsible for securing TikTok's global e-commerce platforms, such as TikTok Shop and Toko, from fraudulent, abusive, or malicious behavior.
Requirements
- 2+ years of experience in delivering ML models in production environments
- Strong coding skills in Python (preferred), and/or Java/C++
- Familiarity with risk control systems or anomaly detection in large-scale, real-time environments
- Experience with LLM post-training applications , especially for agent-based systems
- Experience with: RAG, LangChain, or other agentic LLM systems
- Experience with: Building explainable ML workflows with SHAP, LIME, or counterfactual analysis
- Experience with: Knowledge distillation, BERT, Transformer models
Responsibilities
- Develop and deploy machine learning models (supervised, unsupervised, hybrid) to proactively detect fraud, abuse, and anomalies across seller behavior, user interactions, and transactions.
- Explore cutting-edge techniques including: Retrieval-Augmented Generation (RAG), LangChain-based agents for task decomposition and external knowledge integration
- Design prompt engineering and reasoning workflows that connect structured features, risk indicators, and real-time LLM-based decisions.
- Knowledge Distillation and BERT-style architectures
- Build agentic workflows for complex cases, including modular task agents (e.g., structured data retrieval, open-source search, logical reasoning, decision reflection) orchestrated via a central controller agent.
- Work with large-scale behavioral datasets to uncover fraud signals, design monitoring pipelines, and propose new feature generation strategies.
- Collaborate with risk ops, product managers, and infra engineers to transform insights into scalable and explainable risk control strategies.
Other
- Bachelor’s or Master’s degree in Computer Science, Machine Learning, Statistics, or a related technical field
- Strong communication skills, with the ability to explain technical solutions to non-technical partners
- PhD in Machine Learning, NLP, or a related field
- Background in e-commerce, financial fraud, or trust and safety is highly valued
- Familiarity with LLM integration in decision systems is a strong plus
