Machine Learning Engineer, Risk Data Mining - USDS

The USDS-Platform and Community Integrity (PaCI) team is missioned to: - Protect U.S. TikTok users, including and beyond content consumers, creators, advertisers; - Secure platform health and community experience authenticity; - Build infrastructures, platforms and technologies, as well as to collaborate with many cross-functional teams and stakeholders. The PaCI team works to minimize the damage of inauthentic behaviors on TikTok platforms, covering multiple classical and novel community and business risk areas such as account integrity, engagement authenticity, anti-spam, API abuse, growth fraud, live streaming security and financial safety, etc. In this team, you'll have a unique opportunity to have first-hand exposure to the strategy of the company in key security initiatives, especially in building scalable and robust, intelligent and privacy-safe, secure, and product-friendly systems and solutions. Our challenges are not some regular day-to-day technical puzzles -- You'll be part of a team that's developing novel solutions to first-seen challenges of a non-stop evolution of a phenomenal product eco-system. The work needs to be fast, transferrable, while still down to the ground to make quick and solid differences.

In order to enhance collaboration and cross-functional partnerships, among other things, at this time, our organization follows a hybrid work schedule that requires employees to work in the office 3 days a week, or as directed by their manager/department. We regularly review our hybrid work model, and the specific requirements may change at any time.

Responsibilities:
- Build machine learning solutions to respond to and mitigate business risks in TikTok products/platforms. Such risks include and are not limited to abusive accounts, fake engagements, spammy redirection, scraping, fraud, etc.
- Improve modeling infrastructures, labels, features and algorithms towards robustness, automation and generalization, reduce modeling and operational load on risk adversaries and new product/risk ramping-ups.
- Uplevel risk machine learning excellence on privacy/compliance, interpretability, risk perception and analysis.Minimum Qualifications
- Master or above degree in computer science, statistics, or other relevant, machine-learning-heavy majors.
- Solid engineering skills. Proficiency in at least two of: Linux, Hadoop, Hive, Spark, Storm.
- Strong machine learning background. Proficiency or publications in modern machine learning theories and applications such as deep neural nets, transfer/multi-task learning, reinforcement learning, time series or graph unsupervised learning.
- Ability to think critically, objectively, rationally. Reason and communicate in result-oriented, data-driven manner. High autonomy.