DataVisor is a next generation security company that utilizes industry leading unsupervised machine learning to detect fraudulent activity for financial transactions, mobile user acquisition, social networks, commerce and money laundering. Our solution is used by some of the largest internet properties in the world, including Pinterest, FedEx, AirAsia, Synchrony Financial, Zomato and Ping An, to protect them from the ever-increasing risk of fraud. Our award-winning software is powered by a team of world-class experts in big data, security, and scalable infrastructure. Our culture is open, positive, collaborative, and results driven. Come join us!

Summary

As a platform engineer intern, you will learn how to build a next-generation machine learning platform, which incorporates our secret sauce, UML (unsupervised machine learning) with other SML (supervised machine learning) algorithms. Our team works to improve our core detection algorithms and automate the full training process. As complex fraud attacks become more prevalent, it is more important than ever to detect fraudsters in real-time. The platform team is responsible for developing the architecture that makes real-time UML possible. We are looking for creative and eager-to-learn engineers to help us expand our novel streaming and database systems, which enable our detection capabilities.

This position is ideal for those who are majoring in Computer Science or Computer engineering who would like to gain some hands-on experience in fraud detection and machine learning before graduation. This internship could lead to a full-time position after graduation.

What you'll do:

• Design and build machine learning systems that process data sets from the world’s largest consumer services
• Use unsupervised machine learning, supervised machine learning, and deep learning to detect fraudulent behavior and catch fraudsters
• Build and optimize systems, tools, and validation strategies to support new features
• Help design/build distributed real-time systems and features
• Use big data technologies (e.g. Spark, Hadoop, HBase, Cassandra) to build large scale machine learning pipelines
• Develop new systems on top of realtime streaming technologies (e.g. Kafka, Flink)