Senior AML Modeling Engineer

Coins.ph; United States; Remote; USD 140,000 - 195,000; Full time

Job summary

Coins.ph is seeking a Senior AML Modeling Engineer to develop and optimize AML risk models, improving detection and investigation efficiency. The role emphasizes rule-based and machine learning approaches, including on-chain data analysis and risk scoring across multiple data sources.

You will design transaction monitoring strategies, apply ML models such as XGBoost and LightGBM, and continuously enhance model performance while reducing false positives in a fully remote work environment.

Qualifications

• 5+ years in AML modeling or AML data science.
• Proficient in Python & SQL.
• Strong understanding of AML typologies and detection strategies.
• Experience with ML models (XGBoost, LightGBM) and model evaluation.

Responsibilities

• Develop and optimize AML risk models.
• Design transaction monitoring strategies.
• Analyze on-chain data and integrate diverse data sources.
• Build user risk scoring systems.
• Improve model performance and reduce false positives.
• Support investigation processes in a fully remote environment.

Skills

Python

SQL

AML modeling

Machine learning

XGBoost

LightGBM

Tools

XGBoost

LightGBM

Job description

Coins.ph seeks a Senior AML Modeling Engineer to develop and optimize anti-money laundering risk models, focusing on enhancing detection and investigation efficiency. Candidates with strong AML modeling experience and proficiency in Python and SQL should apply.

As a Senior AML Modeling Engineer at Coins.ph, you will be responsible for developing and optimizing AML risk models, utilizing both rule-based engines and machine learning techniques. Your work will involve designing transaction monitoring strategies, analyzing on-chain data, and creating user risk scoring systems that integrate various data sources.

This role requires a solid understanding of AML typologies and hands-on experience with machine learning models like XGBoost and LightGBM. Success in this position means continuously improving model performance, reducing false positives, and streamlining investigation processes within a fully remote work environment.