9 hours ago

Computer Vision Algorithm Engineer - TikTok E-commerce Knowledge Graph

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI

Last checked: 9 hours agoStatus: Live

Job Summary

Build and improve large-scale product knowledge graphs for TikTok’s global e-commerce experience, powering feed ranking, recommendations, and ads. Work with product managers, data scientists, and product operations to define product strategies and features. Drive knowledge graph construction and e-commerce shopping guide mining, while optimizing computer vision and multimodal models for image/video search, recognition, duplication detection, and shopping video/livestream understanding.

Location: Seattle

Workplace: Onsite

Employment Type: Full time

Job Function: Software Engineering

Key Responsibilities

•Participate in developing massive knowledge graphs of real-world products to support feed ranking, recommendations, and ads.
•Conduct knowledge graph construction, including product/content/feedback understanding and category/brand/SPU construction.
•Optimize and iterate computer vision models for e-commerce use cases such as fine-grain classification, object/subject recognition, feature extraction, logo detection, and brand recognition.
•Handle e-commerce multimodal classification and mining for short videos and livestreams to improve shopping experience.
•Develop e-commerce image and photo search capabilities, including goods duplication algorithms.

Key Requirements

•In-depth knowledge in multimedia and computer vision, including image/video search, classification, recognition, segmentation, object detection, and OCR.
•Experience with graph neural networks and multimodal learning, including unsupervised and self-supervised learning approaches.
•Familiarity with training and deployment of one or more model frameworks such as TensorFlow, PyTorch, or MXNet.
•Understand training acceleration methods such as hybrid precision training and distributed training.

Skills:CollaborationCross-functional communication

Tech Stack:TensorFlowPyTorchMXNet

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

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

TikTok

9 hours ago

Computer Vision Algorithm Engineer - TikTok E-commerce Knowledge Graph

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI

Last checked: 9 hours agoStatus: Live

Job Summary

Location: Seattle

Workplace: Onsite

Employment Type: Full time

Job Function: Software Engineering

Key Responsibilities

•Participate in developing massive knowledge graphs of real-world products to support feed ranking, recommendations, and ads.
•Conduct knowledge graph construction, including product/content/feedback understanding and category/brand/SPU construction.
•Optimize and iterate computer vision models for e-commerce use cases such as fine-grain classification, object/subject recognition, feature extraction, logo detection, and brand recognition.
•Handle e-commerce multimodal classification and mining for short videos and livestreams to improve shopping experience.
•Develop e-commerce image and photo search capabilities, including goods duplication algorithms.

Key Requirements

•In-depth knowledge in multimedia and computer vision, including image/video search, classification, recognition, segmentation, object detection, and OCR.
•Experience with graph neural networks and multimodal learning, including unsupervised and self-supervised learning approaches.
•Familiarity with training and deployment of one or more model frameworks such as TensorFlow, PyTorch, or MXNet.
•Understand training acceleration methods such as hybrid precision training and distributed training.

Skills:CollaborationCross-functional communication

Tech Stack:TensorFlowPyTorchMXNet

Company Brief

TikTok

Industry: Digital Media

Company Size: Enterprise (1,001+ employees)

Growth: Scaleup

Headquarters: Singapore, Singapore

Founded: 2016

Website LinkedIn