Machine Learning Engineer, Multimodal - Intelligent Integrity

TikTok
Singapore
Workplace: OnsiteFull timeFunction: Data Science & Machine LearningEducation: mastersSkills: ["Self-learning","Problem-solving"]

Build and advance large multimodal models for TikTok monetization and Business Integrity. Own algorithm R&D for scalable ad content understanding and security, leveraging LLM/MLLM and AIGC to review e-commerce and short-video ads. Deepen multimodal understanding across text, audio, video, and live streaming; improve risk judgment with interpretable CoT; and explore RL/agent approaches. Develop dedicated models for ad intent recognition, rule retrieval, and compliant-content detection.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
TikTok
TikTok
1 month ago

Machine Learning Engineer, Multimodal - Intelligent Integrity

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 10 hours agoStatus: Live

Job Summary

Build and advance large multimodal models for TikTok monetization and Business Integrity. Own algorithm R&D for scalable ad content understanding and security, leveraging LLM/MLLM and AIGC to review e-commerce and short-video ads. Deepen multimodal understanding across text, audio, video, and live streaming; improve risk judgment with interpretable CoT; and explore RL/agent approaches. Develop dedicated models for ad intent recognition, rule retrieval, and compliant-content detection.
Location: Singapore
Workplace: Onsite
Employment Type: Full time
Job Function: Data Science & Machine Learning
Seniority: Entry level

Key Responsibilities

  • •Focus on ad content understanding and security, running algorithm R&D for large model implementation using LLM/MLLM and AIGC for e-commerce and short-video ad content.
  • •Advance multimodal understanding across text, audio, video, and live streaming; optimize decision-making for high-accuracy autonomous risk judgment with interpretable CoT.
  • •Explore RL/agent applications in multimodal review scenarios and deliver algorithm innovation and engineering implementation for commercial needs.
  • •Develop multimodal content understanding models for ad intent recognition, intelligent rule retrieval, accurate risk judgment, and advertiser creation experience.
  • •Reduce non-compliant content non-detection risks and protect the ad ecosystem security.

Key Requirements

  • •Master’s degree or above in CS, AI, Mathematics, Statistics, or related majors.
  • •1+ year of algorithm R&D or project implementation experience in content understanding or AIGC.
  • •Strong ML/DL foundation with in-depth knowledge of LLM/MLLM, CV, NLP, multimodal fusion, and agent technologies.
  • •Hands-on experience with large model training, fine-tuning, and inference deployment using PyTorch/TensorFlow.
  • •Experience with multimodal large models for content understanding, ad analysis, multimodal representation learning, or intelligent review.
Education:Master's
Skills:Self-learningProblem-solving
Tech Stack:Machine learningDeep learningLLMMLLMAIGCMultimodal fusionAgent technologiesPyTorchTensorFlowPythonC++CVNLP

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