Full-Stack Data Scientist, Hardware Reliability

What you'll do

• Build and maintain data pipelines and infrastructure to improve Starlink hardware reliability.
• Design and manage feature engineering, labeling, and scoring for training and serving reliability models.
• Train, validate, and iterate on machine learning models to predict hardware failures in production and the field.
• Deploy and monitor production models including versioning and scheduled scoring jobs.
• Develop internal analytics tools, APIs, and applications for manufacturing, supply chain, and customer experience teams.
• Build LLM-backed tools featuring retrieval, tool calling, and agentic workflows for engineers and operators.
• Extract actionable signals from unstructured data such as support tickets, chat logs, and images.
• Contribute to core internal and customer-facing software repositories.

What we're looking for

• Bachelor's degree in computer science, data science, mathematics, electrical engineering, or another STEM discipline.
• 4+ years of professional experience in data science, machine learning, or software engineering.
• Strong proficiency in Python and SQL.
• Experience building production data pipelines and deploying machine learning models in production.
• Master's degree in a STEM field or a PhD with at least 3 years of relevant experience.
• Strong understanding of software engineering fundamentals including data structures, algorithms, system design, and concurrency.
• Experience with large language models, retrieval-augmented generation (RAG), tool calling, and agentic workflows.
• Must be a U.S. citizen, permanent resident, or eligible for required export control authorizations.