AI Engineer - Insurance Analytics & Document Intelligence

TG Malaysia; Kuala Lumpur; On-site; MYR 120,000 - 180,000; Full time

Job summary

TG Malaysia, a leading regional insurer, seeks an AI Engineer to develop and deploy ML solutions across underwriting, claims analytics and fraud detection. You will analyze data, engineer features, and optimize models on large datasets while building AI tools to extract information from insurance documents.

You will collaborate with business stakeholders to drive AI governance and best practices, with production deployment and monitoring as part of the lifecycle.

Qualifications

• 3 to 5 years of experience in AI, ML, Data Science or Predictive Analytics.
• Strong Python programming with Pandas and NumPy.
• Experience with ML frameworks such as Scikit-learn, PyTorch, or TensorFlow.
• Knowledge of predictive modeling techniques and anomaly detection.
• Experience deploying ML models into production and monitoring.
• Familiarity with SHAP or LIME is advantageous.

Responsibilities

• Develop and deploy ML models for underwriting, claims analytics and fraud detection.
• Perform data analysis, feature engineering and model optimization on large data sets.
• Build AI solutions for extracting information from insurance documents.
• Support full ML lifecycle from development to production monitoring.
• Collaborate with stakeholders to identify AI-driven improvement opportunities.
• Contribute to AI governance, standards and best practices.

Skills

Python

Pandas

NumPy

Scikit-learn

PyTorch

TensorFlow

XGBoost

LightGBM

Random Forest

Ensemble Models

Anomaly Detection

Model deployment

Model monitoring

Retraining

Explainable AI

Job description

TG Malaysia, a leading regional insurer, seeks an AI Engineer to develop and deploy ML solutions across underwriting, claims analytics and fraud detection. You will analyze data, engineer features, and optimize models on large datasets while building AI tools to extract information from insurance documents.

You will collaborate with business stakeholders to drive AI governance and best practices, with production deployment and monitoring as part of the lifecycle.