Applied Scientist, Traffic Engineering

DESCRIPTION

We are seeking an innovative Applied Scientist to join Amazon's Traffic Engineering organization in developing next-generation bot detection and mitigation capabilities. You will lead the scientific development of real-time anomaly detection systems to identify and counter sophisticated automated threats, including LLM-powered agents, protecting Amazon's websites and subsidiaries worldwide.

This is a critical challenge at the intersection of ML and cybersecurity. With GenAI/LLM-powered bots now capable of mimicking human behavior, evading traditional detections, and monetizing attacks, we must revolutionize our approach from reactive to real-time protection. You'll pioneer ML systems that can detect threats in milliseconds instead of days, protecting Amazon assets and compute while ensuring legitimate bot traffic continues to benefit our business. This role offers the unique opportunity to build first-of-its-kind real-time behavior-based ML models that will safeguard Amazon's global infrastructure. Your work will directly impact millions of customers by ensuring the integrity and availability of Amazon's digital presence while advancing the state-of-the-art in automated threat detection and response.

Key job responsibilities
- Design and develop advanced ML models for real-time detection of programmatic access patterns and anomalous behaviors
- Pioneer new approaches in identifying LLM-based agents and emerging automated threats
- Drive innovation in applying ML/AI techniques to traffic analysis, classification, pattern recognition and automated response systems
- Collaborate with cross-functional teams to implement layered defense strategies
- Mentor junior scientists and contribute to the team's technical direction

About the team
Our team is embarking on a journey to develop the next generation of website traffic management software that protects customers experience. Your work will be highly visible and is instrumental in helping Amazon serve record breaking amounts everyday including flagship events such as Prime Day. If you love building high performance software that's focused on best-in-class networking, data processing, security, and leverages AWS technologies, we have the job for you.

BASIC QUALIFICATIONS

- 3+ years of building models for business application experience
- PhD, or Master's degree and 4+ years of CS, CE, ML or related field experience
- Experience in patents or publications at top-tier peer-reviewed conferences or journals
- Experience programming in Java, C++, Python or related language
- Experience in any of the following areas: algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing