Machine Learning Engineer - NLP, TikTok Business Integrity

$117,000 - $210,960/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

TikTok is the leading destination for short-form mobile video, with a mission to inspire creativity and bring joy. The Business Integrity team is dedicated to technical excellence and user focus, aiming to provide reliable and high-performing platforms and services. This team utilizes advanced technologies such as AIGC large models, deep learning, and machine learning to create a safe and trusted connection between billions of active users and TikTok's commercial products, including advertising, e-commerce, and live broadcasts. By developing a highly concurrent and reliable risk control system, the team can perceive and address risks in real-time, ensuring a secure user experience. The role of a Machine Learning Engineer in this context involves building end-to-end deep learning models and machine learning systems that can automatically review vast amounts of content quickly and efficiently. As a Machine Learning Engineer focusing on Natural Language Processing (NLP), you will be responsible for understanding the content of advertisements, which includes analyzing titles, images, videos, OCR texts, and ASR texts. You will construct various models, such as AIGC models, semantic matching models, and classification models, while also developing text-related strategies like keyword and rule mining. Participation in foundational NLP capacity building is essential, involving tasks such as long/short text classification, sequence-to-sequence models, Named Entity Recognition (NER), and attention mechanisms. This position is integral to enhancing TikTok's ability to manage and review content effectively, contributing to the overall mission of the company.

Responsibilities

• Understand content of advertisements, including titles, images, videos, OCR texts, and ASR texts.
• Construct models such as AIGC model, semantic matching model, and classification model.
• Develop text-related strategies, including keyword mining and rule mining.
• Participate in basic NLP capacity building, including long/short text classification, seq2seq, NER, keyword mining, and attention mechanisms.

Requirements

• Excellent algorithm foundation and programming ability, familiar with mainstream programming languages such as Python/C++.
• Familiar with NLP-related tasks, with practical experience in one or more fields of NLP.
• Knowledge of deep learning and machine learning theories, including Bert, Transformer, Electra, LSTM, LR, SVM, HMM, CRF, Decision Tree, Random Forest.
• Experience with model training frameworks such as TensorFlow, PyTorch, and MXNet.
• Bachelor's degree or above in Computer Science, Computer Engineering, Electrical Engineering, or related fields.
• Strong analytical and problem-solving skills, logical thinking, communication, and collaboration skills.
• Curiosity about new technologies and a strong sense of responsibility, integrity, and reliability.

Nice-to-haves

• Experience in AIGC models 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.