The Credit Risk Management team owns risk policy, analytics, and operations for MoMo's PayLater (Ví Trả Sau) product. The team's scope runs from underwriting and limit management through scoring, fraud and merchant risk control, portfolio monitoring and operations, recovery, and risk reporting to leadership, finance, and lending partners.
What You Will Do
Design and tune underwriting policy - approval rules, score cutoffs, offer structures, and eligibility segments - measured with champion/challenger setups
Run credit-limit management: eligibility criteria, limit increase/decrease decisions, impact sizing, execution, and post-change monitoring
Develop, validate, and monitor risk scores and models; run their production scoring pipelines and manage migrations into decisioning
Run recovery analytics and operations: channel experiments, vendor performance evaluation, and allocation processes
Detect and block cash-out and abuse patterns; maintain merchant- and transaction-level risk controls; assess risk and set launch controls for new products, merchant channels, and payment use cases
Execute account-level risk actions on the live portfolio, with verification and post-action monitoring
Monitor portfolio performance, forecast losses, and investigate portfolio movements
Verify decisioning changes before and after each release; monitor funnel health; investigate production issues in decisioning and data through to root cause with engineering teams
Build and maintain the data pipelines, scheduled jobs, monitoring, and applied AI/automation tooling that risk policies and reporting run on
Produce analyses, decision memos, and recurring risk reporting for leadership, finance, and lending partners; support partner data requests and reconciliations; adapt policy and data handling to regulatory and data-privacy requirements; take end-to-end ownership (PIC) of production decision processes
What You Will Need
Bachelor's degree in a quantitative or engineering field
Hands-on experience in data analytics
Strong SQL on large transactional datasets
Solid statistical grounding for analysis and experimentation
Discipline in verifying results against source data
Clear written communication in Vietnamese and English
Preferred:
Python for analysis
Experience in consumer lending, credit risk, or payments
Experiment design in practice: holdouts, A/B tests, difference-in-differences
Production tooling: Git, Airflow, BigQuery; Spark/Iceberg lakehouse experience
Fluency with AI-assisted workflows, paired with the ability to critically validate AI-generated code and analyses against ground truth
Company Culture:
Our company culture is built on Customer Centricity, Innovation, Teamwork, Excellence in Execution, Constant Learning. We value diversity and inclusivity and strive to create an environment where everyone are inspired to grow and succeed fast together.
Thông tin chung