Full-Stack Data Scientist, Hardware Reliability (Starlink)
About this role
Building data pipelines, machine learning models, and production scoring systems forms the foundation of daily operations on the Starlink Hardware Reliability team at SpaceX. Engineers in this function process telemetry, manufacturing, inventory, field-return, and unstructured support data to generate actionable scores that drive hardware replacement and support decisions. The group operates out of the Bastrop, Texas facility directly alongside the manufacturing lines, building advanced LLM-backed tools such as retrieval, tool calling, and agentic workflows for internal operators.
This role exists to directly improve the reliability of consumer hardware, including dishes, routers, power supplies, and cables deployed to millions of users worldwide. Professionals joining this team must measure whether deployed systems reduce failure rates as new products launch and network scale increases. Candidates who thrive here combine strong Python and SQL engineering capabilities with practical experience deploying models and pipelines into production environments.
Operating in a dynamic environment with tight deadlines requires collaborating across hardware, production, test, inventory, quality, supply chain, and customer experience departments. The position demands independent execution from engineers who can turn complex analyses and failure predictions into tangible design, process, and support modifications.
What you will do
- Build and maintain data pipelines, infrastructure, and software to objectively increase the reliability of Starlink customer hardware.
- Design and operate the feature, label, and scoring data that reliability models train and serve on, handling backfills and data quality.
- Train, validate, and iterate models for hardware failure prediction both on the production line and in the field.
- Deploy and operate models in production through scheduled scoring, versioning, monitoring, and live iteration.
- Contribute to critical Starlink software repositories across core internal and customer-facing codebases.
- Build internal analytics tools, APIs, and applications utilized by hardware, production, quality, and supply chain teams.
- Collaborate across multiple departments to translate analyses and predictions into physical design, process, and support changes.
- Identify customer needs, gather requirements, and execute independently within a dynamic environment featuring tight deadlines.
What you need
- Hold a Bachelor’s degree in computer science, data science, mathematics, electrical engineering, or another STEM discipline.
- Demonstrate at least 4 years of professional experience in data science, machine learning, or software engineering.
- Show strong proficiency in Python and SQL.
- Possess hands-on experience building production data pipelines.
- Demonstrate practical experience deploying machine learning models in production environments.
- Meet U.S. Government export regulations through U.S. citizenship, lawful permanent residency, refugee, or asylee status.
- Commit to working on-site at the Bastrop, Texas facility with availability for extended hours, weekends, and up to 10% travel.
Nice to have
- Master’s degree in computer science, data science, mathematics, or another STEM discipline, or a PhD with 3+ years of relevant experience
- Strong understanding of software engineering fundamentals including data structures, algorithms, system design, concurrency, and maintainable code
- Experience shipping large language models in production, including retrieval-augmented generation (RAG), tool calling, and agentic workflows
- Familiarity with at least one additional programming language such as Go, Java, C++, or C#
- Experience extracting signal from unstructured data like support tickets, chat, call transcripts, and images alongside structured telemetry
Skills and tech stack
Questions candidates ask
What is the remote work policy for this position?
This position is based in Bastrop, TX in the Austin area and requires being on-site. Hybrid or remote work is not considered.
What are the travel and schedule expectations?
Applicants must be willing to work extended hours and weekends as needed. The role also requires being willing to travel up to 10%.
What are the legal or citizenship requirements to apply?
To conform to U.S. Government export regulations, applicants must be a U.S. citizen or national, U.S. lawful permanent resident, refugee, or asylee, or be eligible to obtain the required authorizations from the U.S. Department of State.