Job Description
- Design and build scalable machine learning models using large-scale transaction, behavioral, financial, and credit bureau data to support retail and SME lending, covering underwriting, credit limit management, risk-based pricing, and portfolio optimization.
- Extract actionable insights from complex datasets and apply both traditional statistical methods and advanced deep learning techniques to maximize model performance and business impact.
- Partner closely with Strategy and Business teams to define problems, design modeling solutions, and convert insights into measurable outcomes.
- Collaborate with Data Engineering to deploy models into production, enhance performance in live environments, and establish end-to-end monitoring and evaluation mechanisms.
- Continuously explore state-of-the-art methodologies including sequential modeling, graph learning, causal inference, and multi-task learning to solve challenging risk-decision problems.
- Lead AI/LLM-driven initiatives to enhance modeling efficiency, feature engineering, and advanced data mining capabilities.
Requirements
- Master’s degree or above in Computer Science, Mathematics, Statistics, Quantitative Finance, or related discipline.
- Minimum 3 years hands-on experience in applied machine learning or data science; experience in credit risk or anti-fraud modeling is strongly preferred.
- Proficient in Python with solid experience using scikit-learn and deep learning frameworks such as PyTorch.
- Familiar with big-data ecosystems and distributed computing (Hadoop/Spark/SQL).
- Broad knowledge of machine learning algorithms with deep expertise in at least one area: sequential modeling, graph learning, causal inference, multi-task learning, or reinforcement learning, transfer learning.
- Strong ownership, communication, and cross-functional collaboration skills; ability to independently drive complex modeling projects from ideation to production.