Data Scientist - LEO Terminal Analytics & ML

Amazon; Atlanta (GA); On-site; USD 136,000 - 184,000; Full time

Job summary

Amazon Kuiper Manufacturing Enterprises LLC is seeking a Data Scientist to develop advanced analytics and ML solutions for user terminals in a cross‑functional team including constellation, RF, antenna, silicon, algorithm, and software engineers.

You will build predictive models to identify potential terminal failures in the field and create scalable visualizations and datasets for model training and deployment.

Qualifications

• Master’s degree in Science, Technology, Engineering, or Mathematics (STEM) required or equivalent experience.
• 3+ years of data querying languages (SQL) and scripting (Python, R, SAS, Matlab) experience.
• 3+ years of machine learning/statistical modeling data analysis.
• Experience applying theoretical models in real-world environments.
• Strong communication and analytical skills; ability to work in a small team.

Responsibilities

• Develop statistical tools and models for regression analysis from on-orbit and lab measurements of user terminals.
• Publish documents and create visualizations to communicate insights to stakeholders.
• Create and manage datasets for pre-training and supervised fine-tuning of LLMs.
• Develop scalable visualizations for analyzing user terminal performance.
• Collaborate with multi-disciplinary teams to root-cause failures using data.
• Define metrics and analysis approaches to support product development strategy.

Skills

SQL

Python

ML concepts

Analytical thinking

Communication

Education

Master’s degree in STEM

PhD in STEM

Tools

Python

Perl

Job description

Amazon Kuiper Manufacturing Enterprises LLC is seeking a Data Scientist to develop advanced analytics and ML solutions for user terminals in a cross‑functional team including constellation, RF, antenna, silicon, algorithm, and software engineers.

You will build predictive models to identify potential terminal failures in the field and create scalable visualizations and datasets for model training and deployment.