Xendit provides payment infrastructure across Southeast Asia, with a focus on Indonesia, the Philippines and Malaysia. We process payments, power marketplaces, disburse payroll and loans, provide KYC solutions, prevent fraud, and help businesses grow exponentially. We serve our customers by providing a suite of world-class APIs, eCommerce platform integrations, and easy to use applications for individual entrepreneurs, SMEs, and enterprises alike.
Our main focus is building the most advanced payment rails for Southeast Asia, with a clear goal in mind — to make payments across and within SEA simple, secure and easy for everyone. We serve thousands of businesses ranging from SMEs to multinational enterprises, and process millions of transactions monthly. We’ve been growing rapidly since our inception in 2015, onboarding hundreds of new customers every month, and backed by global top-10 VCs. We’re proud to be featured on among the fastest growing companies by Y-Combinator.
- Remote work might be considered for qualified and highly experienced Candidates
About the Job
The Senior Data Scientist will play a crucial role by leading the development and implementation of risk scoring models across the merchant lifecycle and enhancing the effectiveness and accuracy of our risk detection by developing data science components that can be embedded in multiple risk solutions. You will be the subject matter expert for all Risk teams and partners on all analytical topics such as scoring, modeling, experiment design, hypothesis validation, etc.
The role requires strong model development and data analytics skills as well as the ability to explain the scientific concepts, approach and applications to non-technical audiences. Demonstrated experience with developing risk scoring models at entity and transaction level, experience with cards, strong understanding of various modeling techniques and algorithms, and comfort with dealing with large datasets and prospecting for data in an unstructured environment are a must.
You will collaborate closely with multiple teams within Risk and across Xendit such as Portfolio Monitoring, Risk Operations, Product, Engineering, Data Management, etc. and will interact with multiple senior leaders and their orgs. You will be responsible for developing the cutting edge risk detection and mitigation capabilities using data science and enabling Xendit to assume a proactive posture in managing fraud and credit risk.
Responsibilities
- Lead the risk scoring and risk data science at Xendit
- Develop and implement models for risk scoring of merchants and transaction
- Develop data science tools and components for other Risk teams to enhance the accuracy and effectiveness of our risk rules and strategies
- Partner with other Risk teams on designing and implementing strategies, analyze emerging fraud trends, design experiments, evaluate emerging technologies, etc.
- Balance business and risk needs by partnering with stakeholders on creative methods to enable business growth while keeping risk and losses in check
- Educate the Risk and other teams on data science concepts which they can leverage in their own work
- Do whatever it takes to make Xendit successful
Minimum Qualifications
- 8+ years of experience in risk modeling in financial services, payments or technology companies
- Degree in a quantitative field such as statistics, mathematics, engineering, etc.
- Strong understanding of fraud and credit risk concepts and experience with developing risk scoring solutions
- Experience with Cards and payment transaction risk scoring
- Solid data analysis skills and willingness to do hands-on analysis and data pulls
- Excellent communication and ability to explain complex technical concepts to non-technical audience
- Demonstrated experience of application of multiple modeling techniques to risk management and understanding of latest data science tools and developments
Preferred Qualifications
- Demonstrated experience in hands-on building risk solutions from scratch
- Experience working in an unstructured environment with uneven data availability and reliability
