Data Scientist

About AppsFlyer and Protect360

AppsFlyer is a cutting-edge technology company specializing in mobile attribution and marketing analytics, operating at a massive scale with thousands of servers consuming over 150+ billion mobile app events. Fueled by the AppsFlyer platform, Protect360 is the market-leading anti-fraud solution, protecting advertisers from fraudulent traffic and saving customers millions of dollars. Protect360 detects fraudulent traffic (fake installs and attribution hijacking attempts) in real-time using machine learning, deep learning, and advanced AI techniques applied to massive data streams.

About the Role

We are looking for a Data Scientist to join our team and further improve fraud detection capabilities. This position involves analyzing evolving fraud patterns, developing and deploying advanced prevention components, and leveraging domain expertise, data tools, and modern AI methods to stay ahead of emerging threats.

A partial list of our tech stack includes: Python (and its related scientific stack), Spark, TensorFlow/PyTorch, Kafka, AWS services, Airflow, Scala, BigQuery, and more.

What you'll do

• Mine massive datasets to uncover fraud patterns and prevention opportunities.
• Develop and productionize large-scale ML, DL, and AI models to detect and prevent fraudulent activity.
• Translate business and product needs into scientific, explainable, and high-impact solutions.
• Design and maintain end-to-end ML pipelines - from data ingestion and feature engineering to serving and monitoring in production.
• Collaborate closely with product, engineering, and business teams to drive data-driven decisions.
• Stay current with AI and ML research and evaluate new technologies to strengthen Protect360’s algorithms.

What you have

• M.Sc in Computer Science, Mathematics, Statistics, Engineering, or a related field.
• 2+ years of experience in applied Data Science or Algorithmic Development, preferably in large-scale production environments.
• Hands-on experience in training and fine-tuning machine learning, deep learning, and AI models.
• Strong programming skills in Python and proficiency in SQL.
• Solid understanding of data pipelines, MLOps practices, and working with huge datasets.
• Ability to mentor, collaborate, and communicate complex ideas clearly to diverse audiences.
• A fast learner, problem solver, and end-to-end owner with a strong “can-do” approach.

Bonus Points

• Experience in the ad-tech industry or with fraud detection systems.
• Familiarity with LLMs, generative AI, or representation learning for anomaly detection.
• Proven track record working with large-scale distributed data systems.