Senior Machine Learning / Data Engineering / Data Science Engineer – Credit Risk

Senior Machine Learning / Data Engineering / Data Science Engineer – Credit Risk

Build Next-Generation AI-Powered Credit Decisioning Systems on AWS

We’re seeking a highly experienced engineer (5+ years) with deep expertise in

credit risk modelling ,

lending workflows , and

end-to-end credit decisioning systems . You will design and deploy production-grade models, data pipelines, APIs, and governance frameworks that power modern lending products.

Key Responsibilities

1. Credit Risk Modelling & Decisioning

Develop and validate

credit scoring ,

PD / LGD / EAD , and

behavioural / collections models .

Build

rule-based + ML hybrid underwriting engines

and challenger models.

Design and implement

feature stores , scorecards, segmentation logic, and

reason-code / XAI frameworks .

2. Data Engineering & Architecture (AWS)

Build large-scale

ETL / ELT pipelines

using AWS and open-source stacks (Airflow, Spark, Trino, EKS, S3, EC2).

Implement robust

data quality , lineage tracking, anomaly detection, and incremental loading.

Optimize compute and storage for

performance, reliability, and cost

(including Graviton).

3. MLOps & Governance

Deploy models using

MLflow , Flask, or FastAPI.

Implement

model monitoring , drift detection, CI / CD, and automated retraining workflows.

Ensure compliance with

Basel III, SR 11-7, GDPR, PDPA

using explainability and governance tools.

Build dashboards for model performance, data quality, and underwriting analytics.

4. APIs & Integration

Build and deploy APIs using

API Gateway, Lambda, ECS / Fargate, or EKS .

Integrate ML scoring pipelines with

LOS / LMS , credit bureaus, and partner systems.

5. Product Solutioning & Pre-Sales (Good to Have)

Conduct demos, PoCs, and technical workshops with clients.

Translate business problems into

credit product workflows , decision rules, and risk logic.

Required Skills & Experience

5+ years in

Machine Learning, Data Engineering, or Data Science .

Hands-on experience building

credit risk, fraud, or behavioural ML models .

Strong expertise in

Python, PySpark, SQL , and ML frameworks (scikit-learn, XGBoost, TensorFlow, PyTorch).

Experience with

Spark, Hadoop, Kafka, Trino / Presto .

Strong understanding of

credit underwriting workflows , lending KPIs, and risk decisioning.

Experience building and deploying

ML scoring APIs .

Familiarity with

MLOps best practices

and production ML systems.

Strong grasp of

data governance , regulatory compliance, and model documentation.

Preferred Qualifications

AWS experience with

VPC, ECS / EKS, S3, IAM, Athena, Lambda .

Background in

banks, NBFCs, fintechs, or credit bureaus .

Pre-sales or client-facing solutioning experience.

Exposure to

alternative data modelling .

Degree in

Computer Science, Data Science, Statistics, Engineering , or related fields.