Computer Vision Algorithm Engineer - TikTok E-commerce Knowledge Graph

TikTok; Seattle (WA); On-site; USD 90,000 - 150,000; Full time

Job summary

An innovative company is seeking a Computer Vision Algorithm Engineer to enhance its e-commerce platform. In this role, you'll develop state-of-the-art algorithms and knowledge graphs that improve user experiences and merchant services. Collaborating with a dynamic team, you'll focus on cutting-edge technologies in computer vision and machine learning to optimize product recommendations and ads. If you're passionate about transforming e-commerce through advanced algorithms and enjoy working in a collaborative environment, this opportunity is perfect for you.

Qualifications

• Deep knowledge in multimedia and computer vision, including image/video classification and object detection.
• Experience with training and deploying models using frameworks like TensorFlow and PyTorch.

Responsibilities

• Develop knowledge graphs for product recommendations and ads.
• Optimize computer vision models to enhance merchant product loading/unloading.

Skills

Computer Vision

Machine Learning

Deep Learning

Graph Neural Networks

Multimodal Learning

Self-supervised Learning

Tools

TensorFlow

PyTorch

MXNet

Job description

Computer Vision Algorithm Engineer - TikTok E-commerce Knowledge Graph

Join to apply for the Computer Vision Algorithm Engineer - TikTok E-commerce Knowledge Graph role at TikTok.

Responsibilities

Our team is responsible for developing state-of-the-art CV/NLP/ML algorithms and strategies to improve user consumption experience, inspire merchants' service quality and revenue, and build a fair and flourishing ecosystem on our E-commerce Platform. Specifically, we focus on algorithms for Product Knowledge Graphs within TikTok's global e-commerce business.

What You Will Do:

• Participate in developing massive knowledge graphs of real-world products to support feed ranking, recommendations, and ads.
• Collaborate with product managers, data scientists, and the product strategy & operation team to define product strategies and features.

Responsibilities:

• Construct knowledge graphs, including understanding of products/content/feedback, and building categories, brands, and SPUs.
• Explore implementing Knowledge Graph and Cognitive Graph on TikTok's e-commerce shopping guide.
• Mine e-commerce shopping guide knowledge such as shopping scenes, people, goods matching, and product layering.
• Optimize and iterate computer vision models for e-commerce, including classification, object recognition, feature extraction, logo and brand detection, to improve merchant product loading/unloading.
• Classify e-commerce short videos and live streams, mine multi-modal content, and enhance shopping experiences.
• Develop image search, photo search, and duplicate detection algorithms.
• Research cutting-edge computer vision technologies to evolve algorithms and systems.

Qualifications

Minimum Qualifications:

• Deep knowledge in multimedia and computer vision, including image/video classification, recognition, segmentation, object detection, OCR, graph neural networks, multimodal learning, and self-supervised learning.

Preferred Qualifications:

• Experience with training and deploying models using frameworks like TensorFlow, PyTorch, or MXNet, and understanding training acceleration methods.