Machine Learning Engineer (Risk)

About the Role

SHIELD is a device-first fraud intelligence platform built to help digital businesses worldwide block fake accounts and prevent fraudulent activity. Using SHIELD AI and SHIELD Device ID, the company identifies the source of fraud and delivers actionable intelligence so businesses can respond to both known and emerging threats. SHIELD works with global unicorns such as inDrive, Alibaba, Swiggy, Meesho, and TrueMoney, and operates from locations including Los Angeles, London, Jakarta, Bengaluru, Beijing, and Singapore.

What You Will Do

• Build and apply machine learning solutions to tackle complex risk and fraud-related problems.
• Analyze large volumes of data to uncover patterns and drive fraud detection insights.
• Design, develop, and improve ML algorithms for practical, real-world use cases.
• Create analytical methods that support new approaches to data and information processing.
• Work with both labelled and unlabelled datasets to extract useful signals for the system.
• Contribute beyond ML when needed, including support for other parts of the platform.
• Perform performance analysis, scaling, tuning, and optimization of software systems.
• Help review and strengthen system and software architecture for better stability and efficiency.
• Participate in research and development for fraud detection capabilities.

What We’re Looking For

• A bachelor’s degree in Computer Science, Information Systems with a machine learning focus, or a similar field.
• Strong understanding of databases and data scaling concepts.
• Hands-on experience with machine learning algorithms and the ability to use them in practical scenarios.
• Experience working with MySQL, NoSQL, and columnar databases.
• Programming experience in C++, C, Python, or similar languages is an advantage.
• Exposure to e-payments or e-commerce environments will be considered a plus.
• Good analytical thinking, communication, interpersonal, and presentation abilities.

Additional Information

This position is focused on fraud intelligence and risk applications, with opportunities to explore new technology stacks and work on advanced systems.