Reliability Data Scientist — Full-Stack for Hardware

SpaceX; Town of Texas (WI); On-site; USD 120,000 - 180,000; Full time

Job summary

SpaceX in Bastrop, TX is hiring a Full-stack Data Scientist for the Starlink Reliability team to build data pipelines, models, and production scoring to improve hardware reliability.

You will leverage telemetry, manufacturing, inventory, field-return, and unstructured data to deploy models and tools that inform replacements and support decisions, with on-site work and potential tight deadlines.

Qualifications

• Bachelor's degree in a STEM field.
• 4+ years of professional experience in data science, ML, or software engineering.
• Strong proficiency in Python and SQL.
• Experience building production data pipelines.
• Experience deploying machine learning models in production.

Responsibilities

• Build and maintain data pipelines, infrastructure, and software to improve Starlink hardware reliability.
• Design feature, label, and scoring data for reliability models and backfills.
• Train, validate, and iterate models for hardware failure prediction in production and on the factory line.
• Deploy and operate models in production with versioning, monitoring, and iteration.
• Contribute to core SpaceX software repositories and internal tools.
• Build analytics tools, APIs, and applications used by multiple teams.
• Collaborate across engineering, production, test, inventory, quality, and supply chain to drive design changes.
• Identify customer needs, gather requirements, and work independently under deadlines.

Skills

Python

SQL

Data pipelines

ML in production

APIs/tools

Go/Java/C++

Education

Bachelor's degree in STEM

Master's or PhD (with experience)

Tools

Relational Databases

Data pipeline orchestration

Large-scale data processing

Job description

SpaceX in Bastrop, TX is hiring a Full-stack Data Scientist for the Starlink Reliability team to build data pipelines, models, and production scoring to improve hardware reliability.

You will leverage telemetry, manufacturing, inventory, field-return, and unstructured data to deploy models and tools that inform replacements and support decisions, with on-site work and potential tight deadlines.