Data Scientist I: Ranking & Recommendations (Seattle, Onsite)

Amazon.com Services LLC; Seattle (WA); On-site; USD 108,000 - 160,000; Full time

Benefits offered by this job

Sign-on payments

RSUs

Health insurance (medical, dental, etc

401(k) matching

Paid time off

Parental leave

Job summary

Amazon.com Services LLC in Seattle, WA seeks a Data Scientist to build ranking and recommendation models, perform experiments, and collaborate across science, engineering, and product. You will translate business questions into data science problems and communicate results to engineers, PMs, and leadership.

You’ll own end-to-end analytics from feature engineering to production deployment, partnering with software engineers to run models at scale and maintain performance in a high-traffic

Qualifications

• 1+ years of experience with SQL, Python, or related data tools.
• 2+ years as data scientist, statistician, or quantitative analyst in internet context with big data.
• 1+ years creating or contributing to educational content or textbooks.
• Master’s degree in STEM or equivalent experience.

Responsibilities

• Build and own ML models that rank and recommend offers across the catalog.
• Design and analyze A/B experiments to measure impact.
• Mine large-scale datasets to improve best-offer predictions.
• Translate business questions into data science problems and communicate results.
• Partner with engineers to deploy models at scale and ensure low-latency performance.
• Monitor model performance and iterate as marketplace evolves.

Skills

SQL

Python

Statistics

Data analysis

Experiment design

Education

Master’s degree in STEM

Tools

Hadoop

Spark

Hive

MapReduce

SAS

Matlab

SPSS

Job description

Amazon.com Services LLC in Seattle, WA seeks a Data Scientist to build ranking and recommendation models, perform experiments, and collaborate across science, engineering, and product. You will translate business questions into data science problems and communicate results to engineers, PMs, and leadership.

You’ll own end-to-end analytics from feature engineering to production deployment, partnering with software engineers to run models at scale and maintain performance in a high-traffic