风控算法工程师（本地生活方向） - TikTok研发
Core
Design and maintain TikTok's end-to-end risk control algorithm system for the local life sector, covering merchant onboarding, store claiming fraud, fake group buying, transaction fraud,刷单 arbitrage, fulfillment violations, and account anomalies.
Role type
Senior IC risk control algorithm engineer (local life)
Builds
High-precision, low-latency risk identification and scoring models for merchant and transaction ecosystems
Domain
E-commerce local life + financial risk + anti-fraud
Deliverable
production ML models
Required skills
Machine learning theory, deep learning, classification, ranking, sequence modeling, anomaly detection, XGBoost, DeepFM, Transformer, Graph Neural Networks, Python/C++/Go, PyTorch/TensorFlow, distributed systems, offline training + online inference pipelines
Preferred skills
Agentic AI, LLM fine-tuning (SFT/RLHF), multi-modal representation learning, geo-spatial risk control, behavior sequence anomaly detection, e-commerce local life fraud experience, full lifecycle POC to production deployment
Technologies
XGBoost, DeepFM, Transformer, Graph Neural Networks, PyTorch, TensorFlow, Python, C++, Go
Responsibilities
Design full-link risk control systems, build high-precision models on multi-modal data, build black-market counterattack and emergency response systems, lead technical pre-research and POC validation for Agentic AI and large models, coordinate cross-team technical architecture and iteration
Seniority
Senior, hands-on IC
