Machine Learning Engineer, Risk Data Mining - USDS - TikTok : Job Details

Machine Learning Engineer, Risk Data Mining - USDS

The USDS-Platform and Community Integrity (PaCI) team is missioned to protect U.S. TikTok users, secure platform health and community experience authenticity, and build infrastructures, platforms and technologies in collaboration with cross-functional teams and stakeholders. The PaCI team focuses on mitigating inauthentic behaviors across risk areas such as account integrity, engagement authenticity, anti-spam, API abuse, growth fraud, live streaming security and financial safety. This role offers exposure to company strategy in key security initiatives and the development of scalable, robust, privacy-safe, secure, and product-friendly systems and solutions. The work is fast-paced and focused on delivering clear, transferable impact.

Note: This description reflects the responsibilities and qualifications for the role and may be subject to change. Our organization may follow a hybrid work schedule requiring office presence 3 days a week, or as directed by leadership. Specific requirements may change over time.

Responsibilities

• Build machine learning solutions to identify and mitigate business risks in TikTok products/platforms (e.g., abusive accounts, fake engagements, spam, scraping, fraud).
• Improve modeling infrastructures, labels, features and algorithms to enhance robustness, automation and generalization; reduce modeling and operational load on risk adversaries and support product/risk ramping.
• Advance risk ML excellence with emphasis on privacy/compliance, interpretability, and risk perception analysis.

Qualifications

• Master or higher degree in computer science, statistics, or other relevant, machine-learning-heavy fields.
• Solid engineering skills with proficiency in at least two: Linux, Hadoop, Hive, Spark, Storm.
• Strong machine learning background with experience or publications in modern ML theories and applications (e.g., deep neural nets, transfer/multi-task learning, reinforcement learning, time series, graph learning).
• Ability to think critically and communicate in a result-oriented, data-driven manner with high autonomy.

About USDS

TikTok is the leading destination for short-form mobile video. U.S. Data Security (USDS) is a security-first TikTok division focused on protecting sensitive data and enforcing data protection policies and content assurance protocols for U.S. users. Teams within USDS span Trust & Safety, Security & Privacy, Engineering, User & Product Ops, Corporate Functions and more.

Data Security Statement

This role requires working with systems designed to protect sensitive data and information and may be subject to national security-related screening.

Why Join Us

We aim to inspire creativity and bring joy through a diverse, innovative product. Our culture emphasizes curiosity, humility, impact, and a willingness to learn and innovate as one team.

USDS Reasonable Accommodation

USDS provides reasonable accommodations in our recruitment processes for candidates with disabilities or other protected needs. If you need assistance, please reach out at the provided contact.

Job Information

• Seniority level: Mid-Senior level
• Employment type: Full-time
• Job function: Engineering and Information Technology
• Industries: Technology, Information and Internet
• Base salary range (varies by location): $136,800 – $359,720 annually; total compensation may include bonuses and RSUs

#J-18808-Ljbffr