Machine Learning Engineer/Applied Data Scientist, E-Commerce Risk Control - USDS

About the team
The E-Commerce Risk Control team works to minimize the damage of inauthentic behaviors on Tiktok E-Commerce platforms, covering multiple classical and novel business risk areas such as account integrity, incentive abuse, malicious behaviors, brushing, click-farm, information leakage, 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, transferable, while still down to the ground to make quick and solid differences.

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 account integrity, scalper, deal-hunter, malicious activities, brushing, click-farm, information leakage 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.
- Up-level risk machine learning excellence in privacy/compliance, interpretability, risk perception and analysis.
- Build fraud detection, anomaly detection, and risk-scoring models using supervised, unsupervised, and deep learning techniques.
- Apply graph-based models for detecting fraud networks

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.Minimum Qualifications
- Master degrees in Computer science, Mathematics, Machine Learning, or other relevant STEM majors (e.g. finance if applying for financial fraud roles).
- Experience programming in Java, C++, Python or related language
- 3+ years of hands on experience in building and delivering machine learning models for large-scale projects.
- Track record of developing and implementing models and visualizations using programming and scripting (Scala, Python, R, Ruby, and/or Matlab).
- Strong understanding of anomaly detection, predictive modeling, and Bayesian inference.
- Experience with real-time ML systems, feature engineering, and risk scoring models.
- Experience using various forecasting, machine learning and statistical tools and communicating results, plans and/or risks clearly.
- Ability to think critically, objectively, rationally. Reason and communicate in result-oriented, data-driven manner. High autonomy.

Preferred Qualifications:
- A PhD in CS, Machine Learning, Statistics, Operations Research, or relevant field
- 4+ years of industry experience in predictive modeling and analysis
- Experience collaborating with product, operations and engineering teams is a plus.
- Excellent analytical and communication skills and ability to influence stakeholders.
- Experience in e-commerce / online companies in fraud / risk control functions
- Knowledge of explainable AI (XAI) techniques (SHAP, LIME)