Quantitative (Quant) Engineer
We are seeking highly analytical, data-driven Quantitative Engineers with strong statistical and modelling skills to build and deploy advanced risk models. You will work with large datasets, apply statistical and stochastic techniques, and collaborate across teams to deliver robust risk-modelling solutions.
Project overview: The organisation is driving a major transformation of Clint onboarding & Portfolio monitoring, focusing on automation, AI-driven decisioning, and reimagined end-to-end client journeys. The initiative aims to redesign how clients are onboarded, approved, contracted, activated, and continuously monitored for risk and opportunities. Core priorities include reducing Time to Yes, accelerating contract completion, enabling faster Ready to Transact processes, and improving post-onboarding monitoring. Quantitative Engineers and full-stack engineering teams will build a unified model to enhance onboarding intelligence and ongoing portfolio risk assessment .
Key Responsibilities
Model Development & Validation
- Build, validate, and back-test predictive models for:
- Credit risk, Payment's risk and transaction behaviour
- Anti-financial crime (AFC) indicators
- External market or event-triggered risks
- Develop statistical models that reliably capture portfolio risk exposures.
- Assess predictive power, performance metrics, and robustness of models using historical and stress-scenario data.
- Work with large datasets to detect patterns, identify vulnerabilities, and predict emerging risks.
Risk Domain Expertise
- Strong understanding of credit risk modelling, payments risk, and AFC frameworks
- Build rating models using multivariate data such as transactional behavior, financials, and external market conditions.
- Model a client's repayment ability through quantitative analysis of financial and non-financial indicators.
Cross-Functional Collaboration
- Work closely with risk SMEs, business analysts, and engineering teams to align model development with business needs.
- Communicate findings, methodologies, and risk insights to both technical and non-technical stakeholders.
Required Skills & Qualifications
- Strong quantitative background (eg, Mathematics, Statistics, Data Science, or similar field).
- Hands-on experience building statistical, stochastic, or machine-learning models for risk.
- Proficiency in Python, SQL, or similar analytic languages.
- Experience working with modern data-processing frameworks.
- Domain expertise in at least one of: Credit risk, Payments risk, AFC/fraud detection
Preferred Skills
- Experience in model life cycle management (development, validation, monitoring).
- Exposure to financial portfolio-level risk assessment.
- Familiarity with rating model development using public financial disclosures.
- Prior experience in a bank, fintech, or risk-heavy environment