Data Scientist

Department: Data Analytics, IT

Location: Kuala Lumpur (Hybrid)

Employment Type: Full-Time, Experienced Hire (Minimum 3 years)

Eligibility: Open to Malaysian Citizens

About the Role

The Data Analytics team is seeking an experienced, production-focused Data Scientist to join

our division in Kuala Lumpur. This is an experienced hire position dedicated to designing, deploying, and optimizing the machine learning models that safeguard our financial ecosystem

and automate credit risk decisioning.

Important Application Requirements:

● Experience Level: This role requires immediate, autonomous technical execution within a highly regulated banking environment. This position is strictly for experienced professionals; fresh graduates and entry-level applicants will not be considered.

● Work Authorization: Applicants must be Malaysian Citizens or

Permanent Residents (PR). We are unable to provide visa sponsorship or

consider expatriate applications for this role.

Key Responsibilities

● Model Development & Tuning: Design, build, and maintain high-performing machine

learning models for real-time and batch applications, specifically focusing on Fraud Detection (anomaly detection, transaction fraud, account takeover) and Credit Decisioning (credit scoring, default prediction, optimization).

● Cloud Production Deployment: Deploy, scale, and monitor machine learning models directly into an enterprise cloud production ecosystem. Moving models beyond local environments into live, scalable cloud structures is a core daily responsibility.

● Disciplined CI/CD Pipelines: Work strictly within a full CI/CD environment. You will be

responsible for utilizing robust version control, automated testing, continuous integration,

and automated deployment pipelines rather than running ad-hoc scripts from local machines.

● Regulatory Compliance & Governance: Partner with Risk, Legal, and Compliance

teams to ensure all models comply with strict financial regulations (e.g., BNM guidelines,

AML, KYC, data privacy laws). Document model architectures to meet rigorous model risk management standards.

● Cross-Functional Collaboration: Translate complex statistical insights into clear strategies for stakeholders, credit risk managers, and software engineers to drive automated decision intelligence.

Minimum Candidate Requirements (Screening Criteria)

● Industry Experience: Minimum of 3–5 years of progressive experience as a Data Scientist strictly within the banking, fintech, or financial services industry.

● Production Track Record: Proven, hands-on experience taking at least one machine learning model from development and successfully pushing it to a live cloud production environment using automated pipelines.

● Domain Knowledge: Demonstrable experience working directly with fraud detection frameworks, transactional analysis, or credit risk scoring systems.

Technical Stack & Skills

Core Requirements:

● Programming: Advanced, production-grade proficiency in Python and its data science ecosystem (Pandas, NumPy, Scikit-Learn, XGBoost/LightGBM). Expert-level SQL skills.

● Cloud Platform: Experience building and orchestrating data workloads inside Microsoft Azure (Azure Machine Learning, Azure Data Factory, or Synapse) or relatable enterprise cloud networks.

● Data Warehousing: Experience processing and managing massive data pipelines within Snowflake or Fabric.

● DevOps for ML: Practical knowledge of Git, CI/CD tools (e.g., Azure DevOps, GitHub Actions, GitLab CI/CD), and containerization.

Plus Points & Interview Expectations (Optional):

● Applicants are highly encouraged to share their GitHub repository or code portfolios containing relevant, anonymized work in fraud detection, credit scoring, or advanced MLOps pipelines. Promising candidates will be expected to showcase and present their codebase/architecture during the technical evaluation phase.

Education

● Bachelor's, Master's, or Ph.D. in a quantitative field (Computer Science, Statistics,

Mathematics, Data Science, Econometrics, or financial engineering).