Applied Scientist - Targeting & Reinforcement Learning

Amazon Inc.; Seattle (WA); In loco; USD 143.000 - 193.000; Tempo pieno

Descrizione del lavoro

Amazon is seeking an Applied Scientist to build the science behind targeting across channels and ad formats. You will turn business questions into modeling problems, take solutions from prototype to production, and collaborate with senior scientists, engineers, and business partners.

Role focuses on online optimization, reinforcement learning, incrementality modeling, and agentic targeting workflows. You will work in a fast-paced, collaborative environment with strong quantitative expectations.

Competenze

• 3+ years building models for business applications.
• Publications or patents at top-tier venues valued.
• Proficient in Java, C++, Python or similar.
• Experience with algorithms, data mining, numerical optimization, parallel/distributed computing.
• PhD or MSc with applied research experience.

Mansioni

• Build online optimization (e.g., bandits) and RL methods for business outcomes.
• Develop incrementality and uplift models to measure causal impact.
• Improve segment-based targeting model with new features and architectures.
• Contribute to the intelligence layer by explaining decisions.
• Design and analyze experiments (A/B, causal inference).
• Write production-quality model code and collaborate with engineers.
• Present methods with data-backed recommendations.

Conoscenze

3+ years modeling for business

ML methods experience

Algorithms & data structures

Reinforcement learning / online optim.

Production deployment experience

Patents or publications

Formazione

PhD in a quantitative field

Master's + 3+ years applied research

Strumenti

Java

C++

Python

Descrizione del lavoro

Amazon is seeking an Applied Scientist to build the science behind targeting across channels and ad formats. You will turn business questions into modeling problems, take solutions from prototype to production, and collaborate with senior scientists, engineers, and business partners.

Role focuses on online optimization, reinforcement learning, incrementality modeling, and agentic targeting workflows. You will work in a fast-paced, collaborative environment with strong quantitative expectations.