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

TikTok
Seattle
Workplace: OnsiteFull timeFunction: Data Science & Machine LearningExperience: 2+ yearsEducation: bachelorsSkills: ["Communication"]

Build and deploy machine learning models to detect fraud, abuse, and anomalies across TikTok Shop and Toko, working with seller behavior, user interactions, and transactions. Implement hybrid risk-control systems combining supervised/unsupervised models with retrieval-augmented reasoning and LangChain-based agent workflows. Design prompt and reasoning pipelines, distillation and BERT-style architectures, monitoring pipelines, and explainable risk strategies with product, risk ops, and infra teams.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
TikTok
TikTok
1 month ago

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

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 17 hours agoStatus: Live

Job Summary

Build and deploy machine learning models to detect fraud, abuse, and anomalies across TikTok Shop and Toko, working with seller behavior, user interactions, and transactions. Implement hybrid risk-control systems combining supervised/unsupervised models with retrieval-augmented reasoning and LangChain-based agent workflows. Design prompt and reasoning pipelines, distillation and BERT-style architectures, monitoring pipelines, and explainable risk strategies with product, risk ops, and infra teams.
Location: Seattle
Workplace: Onsite
Employment Type: Full time
Job Function: Data Science & Machine Learning
Seniority: Mid level

Key Responsibilities

  • •Develop and deploy supervised, unsupervised, and hybrid ML models to proactively detect fraud, abuse, and anomalies across seller behavior, user interactions, and transactions.
  • •Implement and explore RAG and LangChain-based agent systems for task decomposition and external knowledge integration.
  • •Design prompt engineering and reasoning workflows connecting structured features, risk indicators, and real-time LLM-based decisions.
  • •Build agentic workflows for complex cases using modular task agents orchestrated via a central controller agent.
  • •Work with risk ops, product managers, and infra engineers to turn insights into scalable, explainable risk control strategies and monitoring pipelines.

Key Requirements

  • •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 risk control systems or anomaly detection in large-scale, real-time environments.
  • •Experience with LLM post-training applications, especially for agent-based systems.
Experience:2+ years
Education:Bachelor's in Computer Science, Machine Learning, Statistics
Skills:Communication
Tech Stack:PythonJavaC++Retrieval-Augmented Generation (RAG)LangChainLLMBERTKnowledge DistillationTransformer modelsPrompt engineeringSHAPLIMECounterfactual analysisGraph neural networksSimilarity searchAgentic workflowsMulti-agent decision-makingDecision reflectionExternal knowledge integration

Company Brief

TikTok
Short-form video platform that lets users create, share, and discover entertainment content through algorithmic recommendations. It also offers advertising and creator tools for brands, influencers, and businesses.
Industry: Digital Media
Company Size: Enterprise (1,001+ employees)
Growth: Scaleup
Headquarters: Singapore, Singapore
Founded: 2016
WebsiteLinkedIn