Applied Scientist, GenAI Fraud & Payments

Amazon Inc.; Seattle (WA); Hybrid; USD 143,000 - 193,000; Full time

Benefits offered by this job

Health insurance

RSUs

401(k) matching

Paid time off

Parental leave

Job summary

Amazon Development Center U.S., Inc. is seeking an Applied Scientist to design, build, and deploy machine learning models that detect, prevent, and mitigate fraudulent activity across the AWS platform.

You will work with massive datasets and apply GenAI techniques to strengthen defenses. You will collaborate with engineering, product, and operations teams to translate business needs into scalable solutions, monitor model performance, and continuously improve robustness in a dynamic threat

Qualifications

• PhD or Master’s with 4+ years in CS/CE/ML.
• 3+ years building models for business use.
• Experience programming in Java, C++, Python.
• Experience with deep learning architectures and optimization.
• Knowledge of algorithms, data structures, and distributed computing.

Responsibilities

• Design, build, and deploy ML models to detect fraud across AWS.
• Analyze large-scale datasets to uncover fraud patterns.
• Explore GenAI techniques to enhance detection capabilities.
• Collaborate with engineering, product, and operations to deliver scalable solutions.
• Monitor model performance and robustness against evolving fraud tactics.
• Communicate findings to technical and non-technical audiences.

Skills

Deep learning

Java/C++/Python

Distributed computing

Algorithms & data structures

Model deployment

Education

PhD or MS in CS/CE/ML

Tools

Java

C++

Python

ML frameworks

Job description

Amazon Development Center U.S., Inc. is seeking an Applied Scientist to design, build, and deploy machine learning models that detect, prevent, and mitigate fraudulent activity across the AWS platform.

You will work with massive datasets and apply GenAI techniques to strengthen defenses. You will collaborate with engineering, product, and operations teams to translate business needs into scalable solutions, monitor model performance, and continuously improve robustness in a dynamic threat