Applied Scientist, Live Data & Analytics — Causal ML

Amazon; Seattle (WA); On-site; USD 143,000 - 193,000; Full time

Benefits offered by this job

Health insurance

401(k) matching

Paid time off

Job summary

Amazon is seeking an Applied Scientist for the DESA team to build production-grade models, experiments, and signals for measuring the value of live video and impacting brand investments. You will own end-to-end lifecycle from research questions to deployment, collaborating with data engineers and business intelligence experts.

You will design causal frameworks, experiments, and ranking signals, with outputs powering downstream systems and executive reporting.

Qualifications

• PhD or Master’s with 4+ years in CS/CE/ML or related field.
• 3+ years of building models for business application.
• Experience programming in Java, C++, Python or related language.
• Experience with PyTorch or JAX software and ML fundamentals.
• Experience with A/B testing, audience segmentation and targeting.
• Experience with large-scale distributed systems (Hadoop, Spark).
• Experience with causal inference methods (incrementality, DD, IV, synthetic control).

Responsibilities

• Design and deploy causal attribution models (incrementality testing, multi-touch).
• Build brand lifecycle models (LTV, CAC) and marketing mix optimization.
• Design and run A/B experiments with proper methodology for new surfaces and ranking changes.
• Build multimodal and generative models for content intelligence at scale.
• Develop ranking and personalization features for downstream distribution systems.
• Build predictive models proving video value to Amazon’s programmatic systems.
• Own full lifecycle from research to production deployment and iteration.
• Present findings to senior leadership and partner teams; translate outputs into decisions.

Skills

3+ years experience

PhD or MS + CS/ML

Java/C++/Python

PyTorch or JAX

A/B testing

Hadoop/Spark

Causal inference methods

Education

PhD or Master’s with 4+ years CS/ML

Tools

Java

C++

Python

PyTorch

JAX

Hadoop

Spark

Job description

Amazon is seeking an Applied Scientist for the DESA team to build production-grade models, experiments, and signals for measuring the value of live video and impacting brand investments. You will own end-to-end lifecycle from research questions to deployment, collaborating with data engineers and business intelligence experts.

You will design causal frameworks, experiments, and ranking signals, with outputs powering downstream systems and executive reporting.