Drimva

Amazon

Data Scientist , Leo Customer Terminal

$136K–$184K

Redmond, WA · Full-time · Posted Oct 5, 2026

Experience
3+ years in data querying languages, scripting languages, or statistical/mathematical software; 3+ years in machine learning/statistical modeling and data analysis.
Education
Bachelor’s degree in electrical engineering, physics, mathematics, or an equivalent field.
Visa sponsorship
Candidates must be a U.S. citizen or national, U.S. permanent resident (current Green Card holder), or lawfully admitted into the U.S. as a refugee or granted asylum.

About the job

Develop analytics and machine-learning solutions for LEO customer terminals, using data to guide design decisions and identify potential field failures.

What you'll do

  • Develop statistical tools and scalable visualizations to analyze terminal performance and support regression decisions using on-orbit and lab measurements.
  • Create and manage datasets for continued pre-training and supervised fine-tuning of LLMs.
  • Work with engineering teams to root-cause failures, communicate insights, and align on metrics and analysis approaches.

What they ask for

  • Experience with SQL and an RDBMS (e.g., Oracle) or Data Warehouse.
  • Bachelor’s degree in electrical engineering, physics, mathematics, or an equivalent field.
  • 3+ years of experience with data querying or scripting languages, or statistical/mathematical software.
  • 3+ years of experience with machine learning/statistical modeling and data analysis, plus experience conducting and documenting trade studies and design trades.

Nice to have

  • Experience implementing algorithms using toolkits and self-developed code; publications at top-tier peer-reviewed conferences or journals.
  • Master's or PhD degree in a relevant field; experience in satellite constellation design, mobility satellite terminals, or phased array designs and implementations.

Pay

136,000.00 - 184,000.00 USD annually (base salary)

Tools

SQL, Oracle, Python, R, SAS, Matlab

AI focus

Develop machine-learning and statistical models to identify potential user-terminal failures; create and manage datasets for continued pre-training and supervised fine-tuning of LLMs.

Model-written summary · the original posting is authoritative

First seen Oct 15, 2026 · Last verified Nov 5, 2026 (UTC)