Quantitative Risk Data Scientist

About the role

Quantitative Risk Data Scientist will join Optasia's Credit Portfolio Optimization team, combining risk management, research and technology to develop algorithmic solutions for revenue and credit‑risk optimization.

Key responsibilities

• Design and implement algorithmic solutions for revenue optimization through credit risk analysis.
• Deliver credit‑risk insights using big‑data risk analytics.
• Develop and implement portfolio risk assessment tools and procedures.
• Conduct detailed risk analysis on micro‑loans and other financial products.
• Identify and evaluate credit risk factors using advanced computational methods on large datasets.
• Develop predictive models, including statistical and machine‑learning approaches, to support risk management strategies.
• Collaborate closely with data scientists and machine‑learning engineers.
• Continuously refine risk assessment methodologies to align with evolving market conditions.

Required profile

• Bachelor’s or master’s degree in Data Science, Statistics, Finance, Mathematics or a related field.
• 2–5 years of experience in quantitative risk analysis, preferably in financial services.
• Proven expertise in developing algorithmic models for revenue and risk optimization.
• Strong proficiency in statistical modeling and machine‑learning techniques.
• Proficiency in Python or R with experience in big‑data risk analytics.
• Demonstrated ability to develop portfolio risk assessment tools.
• Excellent judgment, problem‑solving skills and self‑motivation.

Required skills

• Python
• R
• Statistical modeling
• Machine learning
• Big data analytics

What we offer

• Flexible hybrid working.
• Competitive remuneration package.
• Extra day off on your birthday.
• Performance‑based bonus scheme.
• Comprehensive private healthcare insurance.
• Tech gear and equipment.
• Multicultural working environment.
• Continuous training and access to online platforms.
• CSR activities and festive events.
• On‑site yoga classes and squash court.