Quant jobs / OCBC

AVP, Credit Risk Data Scientist – Credit Risk Modelling

A modelling role in a bank's credit risk team, building and monitoring machine-learning models for consumer, small business and wholesale lending. The models feed underwriting, provisioning and capital decisions.

What you’d work on

Our reading of the posting: what a new hire in this role would most likely spend their first months on.

Develop and maintain machine-learning credit risk models
Monitor and back-test model performance and raise early warnings
Respond to independent validators, auditors and regulators
Turn model outputs into tools for credit decisions, provisioning and capital

What they ask for

Required

Credit risk modelling
Machine learning frameworks (Scikit-Learn, TensorFlow, PyTorch)
Big data tools (Hadoop, Hive, Trino, Spark)
Git and DevOps tooling
Communication with senior management
5–7 years in credit modelling or credit risk

Education: Degree in data science, statistics, maths, computer science or another quantitative discipline
Experience: 5–7 years in credit analysis, credit modelling or credit risk management
Languages and tools: Python
Spark
Hive
Trino
Git
Markets: credit

How to prepare

Build a default prediction model with gradient boosting and compare it with logistic regression
Practise model monitoring: stability metrics, calibration drift and back-testing
Learn IFRS 9 expected credit loss and stress testing basics
Run a Spark pipeline to prepare large credit data sets

What to study

The Risk Quant roadmap sets out the stages for this kind of role, with free resources for each.

Open the roadmap

Apply

Read the full posting on OCBC’s site before applying: requirements, location and pay can change after we check them.

View the posting on OCBC’s site ↗

SelfMadeQuant wrote this summary from the employer’s public posting, last checked 6 November 2026. SelfMadeQuant isn’t affiliated with OCBC and doesn’t handle applications.