TikTok
Machine Learning Engineer (LLM)- E-commerce Risk Control
Seattle, Washington · Full-time · Posted Oct 28, 2026
- Experience
- 2+ years delivering ML models in production environments.
- Education
- Bachelor’s or Master’s degree in Computer Science, Machine Learning, Statistics, or a related technical field.
About the job
Develop and deploy machine learning and LLM-based systems to detect e-commerce fraud, abuse, and anomalies and support scalable risk-control decisions.
What you'll do
- Build production ML models and monitoring pipelines to identify risk signals across seller behavior, user interactions, and transactions.
- Design RAG, agentic, and LLM reasoning workflows for complex risk cases.
- Collaborate with risk operations, product, and infrastructure teams to develop scalable, explainable risk-control strategies.
What they ask for
- Bachelor’s or Master’s degree in Computer Science, Machine Learning, Statistics, or a related technical field.
- 2+ years of experience delivering ML models in production environments.
- Strong coding skills in Python (preferred), and/or Java/C++.
- Familiarity with large-scale, real-time risk-control systems or anomaly detection, and experience with LLM post-training applications, especially agent-based systems.
Nice to have
- PhD in Machine Learning, NLP, or a related field.
- Experience with RAG, LangChain, explainable ML, knowledge distillation, BERT, Transformer models, graph modeling, or e-commerce/financial fraud/trust and safety.
Tools
Python, Java, C++, RAG, LangChain, SHAP, LIME, BERT
AI focus
Applies ML and LLMs to e-commerce risk detection, including RAG, agentic workflows, prompt engineering, LLM post-training, knowledge distillation, and BERT-style architectures.
Model-written summary · the original posting is authoritative