Data Scientist II: End-to-End Experimentation & Impact

Job :  |  Services LLC

Are you excited to figure out not just what is happening but why — and to help build a delivery business that's still taking shape? We're looking for a Data Scientist who thrives on ambiguity and wants to own measurement, modeling, and experimentation across how customers experience Amazon's drone-delivery service.

Your work will span the full data-science toolkit: designing and analyzing experiments (A/B tests), deep-diving customer-experience issues to find root causes, building propensity and behavioral models, forecasting demand, and applying causal methods to understand what actually drives our metrics.

You'll work with large, evolving operational and customer datasets; partner closely with data engineers, scientists, and business stakeholders; and translate rigorous analysis into clear, decision-ready recommendations. Because the business is early and moving fast, you'll help define the right problems as much as solve them — with real room to explore new methods and shape how we measure and improve as we scale.

If you're a curious, collaborative problem-solver who's energized by turning complex, ambiguous data into insight and clear direction, we'd love to hear from you.

Key job responsibilities
- Design and execute data science solutions using a range of methodologies—including machine learning, statistical modeling, and generative AI techniques—to address business problems where the approach is not immediately clear.
- Acquire, transform, and validate large, evolving operational and customer datasets dive deep to investigate anomalies and data quality; and partner with data engineers to bring models and metrics into production.
- Design, run, and analyze experiments (A/B and quasi-experimental studies) to measure impact, size opportunities, and guide product and operational decisions.
- Deep-dive customer-experience issues and metric movements to identify root causes — the why behind the what, including how our metrics and their drivers relate and translate findings into clear, actionable recommendations.
- Communicate complex analyses to technical and non-technical audiences, earn the trust of senior leaders, and influence roadmap and prioritization decisions with your recommendations.
- Own your workstream end-to-end, from problem definition through delivery and ongoing measurement partnering across data engineering, product, and business teams as the business scales.

A day in the life
You might start your morning reviewing model performance metrics before joining a working session with engineers to refine a data pipeline. After lunch, you could be prototyping a new machine learning approach, running experiments, and comparing results against baseline models. Later, you might present preliminary findings to business partners, translating statistical outputs into plain-language recommendations. You will regularly participate in team discussions, scientific reviews, and mentoring conversations that keep you learning and growing.

- 2+ years of data scientist or similar role involving data extraction, analysis, statistical modeling and communication experience
- 2+ years of data querying languages (e.g. SQL, Hadoop/Hive) experience
- 3+ years of machine learning/statistical modeling data analysis tools and techniques, and parameters that affect their performance experience
- Master's degree in a quantitative field, or Bachelor's degree and 5+ years of a quantitative field such as statistics, mathematics, data science, business analytics, economics, finance, engineering, or computer science experience
- Experience applying theoretical models in an applied environment

- Experience in Python, Perl, or another scripting language
-…