Data Scientist - Risk & Fraud

Description

Rakuten Viber is one of the most popular and downloaded apps in the world. Working with us provides a unique opportunity to influence hundreds of millions of our users and to be part of the journey that makes us a super-app. Our mission is to make people’s lives easier by enabling meaningful connections, from precious moments with family and friends, through managing business relationships to pursuing their passions. 

Connecting people across the world is a complex problem with many machine-learning applications. The purpose of this role is to implement models and algorithms to solve complex business problems in risk & fraud domains. Successful outcomes will significantly impact our hundreds of millions of daily active users around the globe.

As a Data Scientist, you will work in a highly collaborative environment with extensive amounts of data to research and develop deep learning models to solve real-world problems and apply them to key risk department initiatives such as predictive fraud detection, performance forecasting and identifying bad actors by using machine learning models.

Responsibilities

• Work with management and partner teams to design and implement solutions for given objectives.
• Commitment to success metrics, ensuring low FP and accurately measuring the impact and model performance
• Lead technical efforts to improve the performance of our Risk & Fraud models and propose initiatives in that domain to shape our long-term risk-mitigation vision.
• Autonomously find solutions to complex data problems and understand the data generation process and the challenges with the data.
• Leverage the extensive data received from our application to enhance model performance and accuracy.

Requirements

• Degree in Statistics, Mathematics or Computer Science.
• Minimum of 2 years of experience in designing, developing and deploying production-level risk & fraud-related models with a proven business impact.
• Worked in a team with peer-review processes.
• Fluency in Python, Pandas/Dask, SQL, PyTorch or Tensorflow. Ability to write readable and maintainable code.
• Strong communication skills. Ability to present technical subjects to non-technical stakeholders.

Advantages

• Advanced degree and knowledge in statistics: Statistical tests, Bayesian inference, MCMC, Likelihood estimators, etc.
• Led the efforts with a proven impact to mitigate Spam, Risk and Fraud at scale.
• Strong passion for machine learning and investing independent time towards learning, researching and experimenting with new innovations in the field.
• Experience working in AWS, NodeJS lambda functions, DataDog and operational experience

Skills