Machine Learning Engineer (LLM)- E-commerce Risk Control

Responsibilities

Team Introduction
The E-Commerce Risk Control (ECRC) team is responsible for securing TikTok's global e-commerce platforms, such as TikTok Shop and Toko. We safeguard buyers, sellers, creators, and the ecosystem from fraudulent, abusive, or malicious behavior. Our mission is to make TikTok the safest and most trusted online marketplace worldwide. We achieve this through:
- Advanced machine learning systems to detect and prevent evolving business risks (e.g., account takeovers, collusion, incentive abuse, brushing, click-farms);
- A hybrid approach combining machine learning models, retrieval-augmented reasoning, and multi-agent decision-making systems;
- Cross-functional collaboration with product, ops, security, and trust teams.

What You'll Do
- 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.

Why Join Us
- Work on real-world, high-impact challenges in global risk mitigation
- Be part of a cutting-edge ML + LLM team shaping the future of risk intelligence
- Enjoy a culture of autonomy, innovation, and cross-disciplinary collaboration

Qualifications

Minimum Qualifications
-Bachelor's or Master's degree in Computer Science, Machine Learning, Statistics, or a related technical field
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
-Strong communication skills, with the ability to explain technical solutions to non-technical partners

Preferred Qualifications
-PhD in Machine Learning, NLP, or a related field
-Experience with:
- RAG, LangChain, or other agentic LLM systems
- Building explainable ML workflows with SHAP, LIME, or counterfactual analysis
- Knowledge distillation, BERT, Transformer models
- Graph-based modeling, graph neural networks, or similarity search
- Background in e-commerce, financial fraud, or trust and safety is highly valued
- Familiarity with LLM integration in decision systems is a strong plus

Job Information

[For Pay Transparency] Compensation Description (annually)

The base salary range for this position in the selected city is $153900 - $300960 annually.

Compensation may vary outside of this range depending on a number of factors, including a candidate's qualifications, skills, competencies and experience, and location. Base pay is one part of the Total Package that is provided to compensate and recognize employees for their work, and this role may be eligible for additional discretionary bonuses/incentives, and restricted stock units.

Benefits may vary depending on the nature of employment and the country work location. Employees have day one access to medical, dental, and vision insurance, a 401(k) savings plan with company match, paid parental leave, short-term and long-term disability coverage, life insurance, wellbeing benefits, among others. Employees also receive 10 paid holidays per year, 10 paid sick days per year and 17 days of Paid Personal Time (prorated upon hire with increasing accruals by tenure).

The Company reserves the right to modify or change these benefits programs at any time, with or without notice.

For Los Angeles County (unincorporated) Candidates:

Qualified applicants with arrest or conviction records will be considered for employment in accordance with all federal, state, and local laws including the Los Angeles County Fair Chance Ordinance for Employers and the California Fair Chance Act. Our company believes that criminal history may have a direct, adverse and negative relationship on the following job duties, potentially resulting in the withdrawal of the conditional offer of employment:

1. Interacting and occasionally having unsupervised contact with internal/external clients and/or colleagues;

2. Appropriately handling and managing confidential information including proprietary and trade secret information and access to information technology systems; and

3. Exercising sound judgment.

Responsibilities

Responsibilities

Team Introduction
The E-Commerce Risk Control (ECRC) team is responsible for securing TikTok's global e-commerce platforms, such as TikTok Shop and Toko. We safeguard buyers, sellers, creators, and the ecosystem from fraudulent, abusive, or malicious behavior. Our mission is to make TikTok the safest and most trusted online marketplace worldwide. We achieve this through:
- Advanced machine learning systems to detect and prevent evolving business risks (e.g., account takeovers, collusion, incentive abuse, brushing, click-farms);
- A hybrid approach combining machine learning models, retrieval-augmented reasoning, and multi-agent decision-making systems;
- Cross-functional collaboration with product, ops, security, and trust teams.

What You'll Do
- 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.

Why Join Us
- Work on real-world, high-impact challenges in global risk mitigation
- Be part of a cutting-edge ML + LLM team shaping the future of risk intelligence
- Enjoy a culture of autonomy, innovation, and cross-disciplinary collaboration

Qualifications

Qualifications

Minimum Qualifications
-Bachelor's or Master's degree in Computer Science, Machine Learning, Statistics, or a related technical field
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
-Strong communication skills, with the ability to explain technical solutions to non-technical partners

Preferred Qualifications
-PhD in Machine Learning, NLP, or a related field
-Experience with:
- RAG, LangChain, or other agentic LLM systems
- Building explainable ML workflows with SHAP, LIME, or counterfactual analysis
- Knowledge distillation, BERT, Transformer models
- Graph-based modeling, graph neural networks, or similarity search
- Background in e-commerce, financial fraud, or trust and safety is highly valued
- Familiarity with LLM integration in decision systems is a strong plus