Drimva

Motional

Senior Data Scientist, Systems Performance

$149K–$198K

Boston, Massachusetts, United States +7 · Remote · Senior · Full-time · Posted Oct 8, 2026

Location
Boston, Massachusetts, United States
Las Vegas, Nevada, United States
Pittsburgh, Pennsylvania, United States
Remote U.S.
Boston, Massachusetts, United States
Las Vegas, Nevada, United States
Pittsburgh, Pennsylvania, United States
Remote U.S.
Experience
5+ years of industry experience.
Education
Bachelor's or higher degree in a related quantitative field; Master's or PhD preferred.

About the job

Leads the development and assessment of rigorous performance evaluation methods for Motional’s autonomous driving system, supporting safety cases, launch readiness, and engineering decisions.

What you'll do

  • Develop and monitor evaluation frameworks, metrics, statistical methods, and data quality for simulation and on-road performance.
  • Analyze fleet and evaluation data to identify anomalies, edge cases, coverage gaps, and relationships between simulation and on-road results; improve test coverage.
  • Partner with engineering and safety teams to inform launch decisions, communicate findings, and establish developer self-service evaluation practices.

What they ask for

  • 5+ years of industry experience solving complex problems with large datasets.
  • Bachelor's or higher degree in a quantitative field such as Computer Science, Data Science, Robotics, Physics, or Mathematics.
  • Strong Python and SQL skills and experience using data analysis libraries with large, complex datasets.
  • Experience applying advanced statistical and ML methods, including statistical analysis, hypothesis testing, and causal analysis.

Nice to have

  • Master's or PhD.
  • Experience in autonomous driving or robotics; adversarial scenario generation, simulation, data pipelines/distributed compute, or automotive safety standards.

Pay

$149,000 — $198,500 USD (base salary)

Tools

Python, SQL, AWS, Transformers, ISO 26262, ISO 21448, SOTIF

AI focus

Introduces ML methods where they improve rigor and scale in performance evaluation; applies statistical and ML techniques to autonomous-vehicle performance data. Deep learning, sequence modeling, and probabilistic ML are preferred areas.

Model-written summary · the original posting is authoritative

First seen Oct 27, 2026 · Last verified Nov 4, 2026 (UTC)