Senior Machine Learning Engineer (CV/NLP/Multimodal/LLM/Agent)-E-Commerce Government
TikTok
Posted 12 days ago
About this role
About
The e-commerce industry has seen tremendous growth in recent years and has become a hotly contested space amongst leading Internet companies, and its future growth cannot be underestimated. With millions of loyal users globally, we believe TikTok is an ideal platform to deliver a brand new and better e-commerce experience to our users. We aim to bring discovery, inspiration, and joy back to shopping by making TikTok the commerce channel of choice for merchants, creators, and affiliates.With millions of loyal users globally, we believe TikTok is an ideal platform to deliver a brand new and better e-commerce experience to our users. We are looking for passionate and talented people to join our product and operations team, to build an e-commerce ecosystem that is innovative, secure and intuitive for our users and brands.
About the Team
The Governance and Experience Algorithm team was established in September 2020 and its main job is to support the following businesses with the most advanced AI technology：
- Combat any kinds of risks/violations issues in E-commerce scenarios.
- Build a safe E-commerce ecosystem and improve platform service capabilities
Responsibilities:
- Responsible for identifying algorithms for risk/violation/low-quality issues in e-commerce scenarios such as products, shopping cart short videos, and live streaming with products.
- Responsible for mining and identifying algorithms to detect fraudulent behaviors and identify risky, violated, or low-quality merchants and creators.
- Responsible for optimizing algorithms for large-scale brand libraries, products, and content deduplication/clustering.
- Responsible for data construction, instruction fine-tuning, CoT, alignment, and other work for large models in the e-commerce domain, aiming for ultimate effect optimization in the e-commerce domain.
- Responsible for exploring reinforcement learning and operational research algorithms in intelligent dispatching and intelligent audit scheduling to improve audit quality and efficiency.
- Responsible the research and development of multi-agent tools, models, engines, and platforms to enhance automatic planning, generalized decision-making, and multimodal interaction capabilities in e-commerce scenarios. Deliver Agent-based solutions to address problems beyond the reach of existing methods and models, identify capability gaps in current models, and feed insights from real-world applications back into foundational model iteration.
- Drive performance and stability optimization of Agent Systems, including but not limited to system resource utilization, environment interaction latency, and overall cost efficiency. Abstract and generalize capabilities from business requirements, define the platform roadmap, and build a stable, reliable Agent infrastructure.
What You Will Do:
- Optimize various basic algorithms such as NLP, vision, multimodal, search, graph, LLM, Agent etc. to provide support for governance business, explore cutting-edge technologies, and apply them to e-commerce business scenarios.
- Streamline the optimization and iteration process for computer vision models in e-commerce settings, including fine-grained classification of product images, product object recognition, product subject recognition, feature extraction, logo detection, brand recognition, etc.
- Optimize video classification, multimodal content mining, and multimodal content understanding of e-commerce short videos and live broadcasts, and optimize the e-commerce short video shopping experience.
- Optimize the risk identification model related to text content in e-commerce scenarios, such as product copywriting, picture text, and voice descriptions.
- Optimize the risk mining algorithm for comments, reports, and other public opinion content related to products/short videos/live broadcasts, and improve the platform governance effect.
- Responsible for the research of large-scale multimodal (vision, speech, natural language, etc.) algorithms and their implementation in e-commerce scenarios.
- Extract extensive data from various entities, such as content in e-commerce live broadcasts, products, merchants, and influencers. Model large-scale networks to support business scenarios like content understanding, multimodal representation, and community mining for problem-solving purposes.
- Participate in the construction of a large-scale graph storage and graph learning platform, supporting the basic ability of graph learning with billions of nodes and edges.
The e-commerce industry has seen tremendous growth in recent years and has become a hotly contested space amongst leading Internet companies, and its future growth cannot be underestimated. With millions of loyal users globally, we believe TikTok is an ideal platform to deliver a brand new and better e-commerce experience to our users. We aim to bring discovery, inspiration, and joy back to shopping by making TikTok the commerce channel of choice for merchants, creators, and affiliates.With millions of loyal users globally, we believe TikTok is an ideal platform to deliver a brand new and better e-commerce experience to our users. We are looking for passionate and talented people to join our product and operations team, to build an e-commerce ecosystem that is innovative, secure and intuitive for our users and brands.
About the Team
The Governance and Experience Algorithm team was established in September 2020 and its main job is to support the following businesses with the most advanced AI technology：
- Combat any kinds of risks/violations issues in E-commerce scenarios.
- Build a safe E-commerce ecosystem and improve platform service capabilities
Responsibilities:
- Responsible for identifying algorithms for risk/violation/low-quality issues in e-commerce scenarios such as products, shopping cart short videos, and live streaming with products.
- Responsible for mining and identifying algorithms to detect fraudulent behaviors and identify risky, violated, or low-quality merchants and creators.
- Responsible for optimizing algorithms for large-scale brand libraries, products, and content deduplication/clustering.
- Responsible for data construction, instruction fine-tuning, CoT, alignment, and other work for large models in the e-commerce domain, aiming for ultimate effect optimization in the e-commerce domain.
- Responsible for exploring reinforcement learning and operational research algorithms in intelligent dispatching and intelligent audit scheduling to improve audit quality and efficiency.
- Responsible the research and development of multi-agent tools, models, engines, and platforms to enhance automatic planning, generalized decision-making, and multimodal interaction capabilities in e-commerce scenarios. Deliver Agent-based solutions to address problems beyond the reach of existing methods and models, identify capability gaps in current models, and feed insights from real-world applications back into foundational model iteration.
- Drive performance and stability optimization of Agent Systems, including but not limited to system resource utilization, environment interaction latency, and overall cost efficiency. Abstract and generalize capabilities from business requirements, define the platform roadmap, and build a stable, reliable Agent infrastructure.
What You Will Do:
- Optimize various basic algorithms such as NLP, vision, multimodal, search, graph, LLM, Agent etc. to provide support for governance business, explore cutting-edge technologies, and apply them to e-commerce business scenarios.
- Streamline the optimization and iteration process for computer vision models in e-commerce settings, including fine-grained classification of product images, product object recognition, product subject recognition, feature extraction, logo detection, brand recognition, etc.
- Optimize video classification, multimodal content mining, and multimodal content understanding of e-commerce short videos and live broadcasts, and optimize the e-commerce short video shopping experience.
- Optimize the risk identification model related to text content in e-commerce scenarios, such as product copywriting, picture text, and voice descriptions.
- Optimize the risk mining algorithm for comments, reports, and other public opinion content related to products/short videos/live broadcasts, and improve the platform governance effect.
- Responsible for the research of large-scale multimodal (vision, speech, natural language, etc.) algorithms and their implementation in e-commerce scenarios.
- Extract extensive data from various entities, such as content in e-commerce live broadcasts, products, merchants, and influencers. Model large-scale networks to support business scenarios like content understanding, multimodal representation, and community mining for problem-solving purposes.
- Participate in the construction of a large-scale graph storage and graph learning platform, supporting the basic ability of graph learning with billions of nodes and edges.