Senior Data Scientist, Algorithm (Lending & Onboarding)

Airwallex3 days ago

Location

SG - Singapore

Type

Full Time

Salary

USD 150,000 – 220,000

Level

Senior

Role

Data Scientist

Posted

Jul 22, 2026

Full TimeSenior

The role

Summary

Senior Data Scientist specializing in algorithm development for lending and onboarding at Airwallex, a $11B fintech platform. You'll design and deploy real-time machine learning models for fraud detection, account takeover prevention, and credit risk assessment while partnering with cross-functional teams to translate business requirements into scalable, data-driven solutions that protect customers and drive lending platform growth across global markets.

What you'll do

Real-Time ML Model Development: Design, develop, and deploy real-time machine learning models for critical risk applications including account takeover prevention, fraud decisioning, and customer protection. Ensure models meet production performance requirements and scale across millions of transactions while maintaining sub-second latency for online decisioning systems.

Credit Risk Modeling: Build sophisticated credit risk models and analytical frameworks to assess merchant creditworthiness, predict default probabilities, and support underwriting decisions. Develop scorecards, segmentation strategies, and portfolio analytics to enable growth of Airwallex's lending business while managing credit exposure.

Business Problem Translation: Translate complex business requirements from fraud, credit, onboarding, and risk domains into well-defined analytical and modeling problems. Work with stakeholders to understand success metrics, constraints, and trade-offs to ensure solutions deliver measurable business impact.

Performance Monitoring & Analytics: Design comprehensive performance monitoring frameworks, KPI dashboards, and decision-support tools that provide real-time visibility into model health, risk metrics, and business outcomes. Build alerting systems and analytical tools that enable rapid detection and response to model degradation or emerging threats.

Cross-Functional Collaboration: Partner with Product, Engineering, Operations, Finance, and Compliance teams to operationalize data science solutions into production systems. Drive adoption of advanced data science techniques, experimentation frameworks, and best practices to improve customer experiences and business outcomes at scale.

What we look for

Technical

Python ProgrammingProficiency in Python for data manipulation, statistical analysis, model development, and production-level code. Experience with scientific computing libraries such as NumPy, Pandas, scikit-learn, and familiarity with model deployment frameworks.

SQL & Database QueryingAdvanced SQL skills for querying large datasets, performing complex aggregations, and extracting features from transactional and behavioral data. Experience optimizing queries for performance and working with both relational and time-series databases.

Machine Learning & Statistical ModelingStrong foundation in machine learning techniques including supervised learning, classification, regression, and ensemble methods. Understanding of statistical concepts, hypothesis testing, and model evaluation metrics. Experience with techniques applicable to financial risk modeling.

Large-Scale Data ProcessingExperience working with big data technologies and large datasets. Familiarity with distributed computing concepts, data warehousing, and scalable data pipelines for handling high-volume transaction data.

Education

Quantitative Bachelor's DegreeBachelor's degree or above in a quantitative discipline such as Statistics, Mathematics, Economics, Computer Science, Engineering, Physics, or related field. Strong mathematical foundation and exposure to data analysis coursework.

Experience

Data Science & Analytics ExperienceMinimum 3+ years of professional experience in data science, analytics, risk strategy, quantitative research, or related roles. Demonstrated ability to own analytical projects end-to-end, from problem definition through model validation and business impact assessment.

Stakeholder ManagementProven experience translating technical findings into business insights and collaborating with non-technical stakeholders. Ability to communicate complex analytical concepts clearly to Product, Engineering, and business teams.

Problem-Solving with DataTrack record of solving ambiguous business problems using data-driven approaches. Comfortable working with messy, incomplete datasets and designing robust solutions despite data quality challenges.

Skills

Required skills

PythonCore programming language for data science work, model development, and feature engineering

SQLEssential for data extraction, exploration, and feature creation from transactional databases

Statistical AnalysisFoundation for hypothesis testing, A/B experimentation, and model evaluation

Machine Learning AlgorithmsUnderstanding of classification, regression, and ensemble methods for risk modeling

Data Manipulation & AnalysisProficiency with Pandas, NumPy, and similar libraries for exploratory data analysis

Problem-SolvingAbility to break down complex business problems into analytical components

Nice to have

Credit Risk ModelingHands-on experience building credit scorecards, probability of default models, or loss given default models in financial services

Fraud Detection & ATO PreventionExperience developing machine learning solutions for fraud prevention, account takeover detection, or anomaly detection in fintech or payments

Model Development & ValidationHands-on experience training, validating, backtesting, and monitoring machine learning models in production environments

Risk Rules & Decision Strategy DesignExperience designing rule-based systems, decision trees, or threshold optimization strategies for risk management and compliance

Real-Time SystemsFamiliarity with real-time data processing, streaming data pipelines, or low-latency ML inference systems

Fintech & Payments Domain KnowledgeUnderstanding of payments infrastructure, lending platforms, KYC/AML regulations, or financial crime risks

Advanced Analytics PlatformsExperience with cloud data platforms (Snowflake, BigQuery, Redshift) or ML platforms for model operationalization

Compensation & benefits

Salary

USD 150,000 – 220,000 (annual)

Stock options

Available

Benefits

High-Impact Problem Ownership

Lead end-to-end machine learning initiatives that directly influence fraud prevention, credit decisions, and risk management across millions of global transactions, with measurable business outcomes and customer protection.

Collaborative, World-Class Team

Work alongside exceptional data scientists, engineers, and product leaders at a $11B fintech unicorn. Collaborate with cross-functional teams including Product, Engineering, Compliance, and Operations in a high-growth, innovative environment.

Advanced Data Science Culture

Drive adoption of cutting-edge data science techniques, experimentation frameworks, and AI-powered solutions. Contribute to establishing best practices in risk modeling, feature engineering, and real-time ML systems at scale.

Fintech Domain Leadership

Develop deep expertise in payments, lending, fraud prevention, and credit risk management. Work on complex problems at the intersection of financial services, machine learning, and risk management with global implications.

Founder-Like Ownership

Experience rapid career growth and true ownership of projects from concept to production. Operate with founder-level autonomy while supported by a 2,300+ person global team and world-leading investors.

Global Impact at Scale

Influence business outcomes for 250,000+ customers including Fortune 500 companies (Brex, Rippling, Navan, Qantas, SHEIN). Your models and decisions impact millions of daily transactions across 27 global offices.

Interview process

1
Initial Screening & Phone Conversation — Brief conversation with Airwallex recruiting to discuss background, experience with data science and risk modeling, and alignment with role requirements. Expected duration: 20-30 minutes.
2
Take-Home Analytics/Modeling Challenge — Practical assignment involving real-world data science problem related to fraud, credit risk, or classification modeling. You'll write Python/SQL code, perform exploratory analysis, build models, and document your approach. Typical scope: 3-4 hours.
3
Technical Interview with Senior Data Scientist — Deep dive discussion of your take-home solution, machine learning fundamentals, statistical concepts, and problem-solving approach. You'll walk through your models, discuss trade-offs, and answer questions about ML best practices and risk modeling. Duration: 60 minutes.
4
Business Impact & Cross-Functional Interview — Conversation with Product, Engineering, or Operations stakeholder focused on translating business problems into data solutions. Discuss how you've partnered with non-technical teams, managed competing priorities, and delivered measurable impact. Duration: 45 minutes.
5
Risk Domain Discussion & Strategy Interview — Meet with risk strategy or lending team members to discuss your experience with fraud, credit, or related risk domains. Explore your thinking on model monitoring, decision frameworks, and regulatory considerations. Duration: 45 minutes.
6
Hiring Manager Final Round — Comprehensive conversation with the hiring manager covering role expectations, team dynamics, career growth opportunities, and your motivations. Discuss how you work with ambiguous problems, drive ownership, and learn in fast-paced environments.