Machine Learning Engineer (CV/NLP/Multimodal/LLM) -E-commerce Governance

$145,000 - $250,000/Yr

Tiktok - San Jose, CA

Full-time - Mid Level

San Jose, CA

Computing Infrastructure Providers, Data Processing, Web Hosting, and Related Services

About the position

As a Machine Learning Engineer specializing in Computer Vision (CV), Natural Language Processing (NLP), Multimodal, and Large Language Models (LLM) at TikTok, you will play a pivotal role in enhancing the governance and experience algorithms that support our e-commerce platform. Your primary focus will be on identifying and developing algorithms that address risks, violations, and low-quality issues within e-commerce scenarios, including product listings, shopping cart videos, and live streaming content. You will be responsible for mining and detecting fraudulent behaviors, optimizing algorithms for large-scale brand libraries, and ensuring the integrity of our e-commerce ecosystem. In this role, you will engage in data construction and fine-tuning of large models tailored for the e-commerce domain, aiming for optimal performance and effectiveness. You will explore advanced techniques such as reinforcement learning and operational research algorithms to enhance audit quality and efficiency in intelligent dispatching and scheduling. Your work will involve optimizing various foundational algorithms, including those related to NLP, vision, multimodal processing, search, and graph algorithms, to support governance business and apply cutting-edge technologies to real-world e-commerce scenarios. You will also streamline the optimization process for computer vision models, focusing on tasks such as fine-grained classification of product images, object recognition, feature extraction, and logo detection. Additionally, you will work on improving video classification and multimodal content understanding for e-commerce short videos and live broadcasts, enhancing the overall shopping experience for users. Your responsibilities will extend to optimizing risk identification models related to text content and public opinion, ensuring that our platform maintains a high standard of governance and user trust. As part of your role, you will extract and analyze extensive data from various entities, including live broadcast content, products, merchants, and influencers, to support business scenarios like content understanding and community mining. You will also participate in the development of a large-scale graph storage and learning platform, contributing to the foundational capabilities of graph learning with billions of nodes and edges.

Responsibilities

• Identify algorithms for risk, violation, and low-quality issues in e-commerce scenarios.
• Mine and identify algorithms to detect fraudulent behaviors and identify risky merchants and creators.
• Optimize algorithms for large-scale brand libraries and content deduplication/clustering.
• Conduct data construction, instruction fine-tuning, and alignment for large models in the e-commerce domain.
• Explore reinforcement learning and operational research algorithms to improve audit quality and efficiency.
• Optimize basic algorithms such as NLP, vision, multimodal, search, graph, and LLM for governance business.
• Streamline optimization processes for computer vision models in e-commerce settings.
• Optimize video classification and multimodal content understanding for e-commerce short videos and live broadcasts.
• Enhance risk identification models related to text content in e-commerce scenarios.
• Optimize risk mining algorithms for comments and reports related to products and short videos.
• Research large-scale multimodal algorithms and their implementation in e-commerce scenarios.
• Extract extensive data from various entities to support business scenarios like content understanding and community mining.
• Participate in the construction of a large-scale graph storage and learning platform.

Requirements

• Bachelor's degree or above in computer science or related field.
• Solid coding skills with proficiency in Python, Go, or C++ in a Linux environment.
• Strong foundation in data structures and algorithms, with practical experience in machine learning and deep learning.
• Familiarity with 1-2 areas in NLP, computer vision, multimodal, graph algorithms, search algorithms, text/data mining, and LLM.
• Excellent analytical and problem-solving skills, with a passion for challenging problems.
• Good team spirit and strong communication skills.
• Experience in platform governance, audit, risk control, or content security in e-commerce is preferred.
• Fluent English listening, speaking, reading, and writing skills are preferred.
• Experience studying, working, or living overseas is preferred.

Nice-to-haves

• Experience in platform governance/audit/risk control/content security or overseas internet/e-commerce business is preferred.
• Fluent English listening, speaking, reading, and writing skills are preferred.
• Experience studying, working, or living overseas is preferred.

Benefits

• 100% premium coverage for employee medical insurance, approximately 75% for dependents.
• Health Savings Account (HSA) with company match.
• Dental, Vision, Short/Long term Disability, Basic Life, Voluntary Life, and AD&D insurance plans.
• Flexible Spending Account (FSA) options for healthcare and dependent care.
• 10 paid holidays per year plus 17 days of Paid Personal Time Off (PPTO).
• 10 paid sick days per year.
• 12 weeks of paid Parental leave and 8 weeks of paid Supplemental Disability.
• Mental and emotional health benefits through EAP and Lyra.
• 401K company match.
• Gym and cellphone service reimbursements.