Senior Robotics Engineer, AV Performance Diagnosis & Evaluation

Motional•Boston, MA

7d•$149,000 - $198,500•Hybrid

About The Position

The Senior Robotics Engineer will join the Systems Readiness and Performance team, which bridges software development and real-world deployment. The team drives system design, verifies and validates the autonomy stack, and defines, measures, and validates system performance targets. It works with autonomy, infrastructure, and operations stakeholders to build the safety case for commercial launch of driverless IONIQ 5 robotaxis in Las Vegas. The engineer will investigate and diagnose complex autonomous vehicle behaviors across on-road, resimulation, and synthetic simulation environments. This role owns ambiguous problem spaces end to end, using Python, custom Spaceship tooling, and data visualization platforms to perform root-cause analysis across the autonomy stack. Findings will be synthesized into clear summaries that support release narratives, executive insights, and cross-functional communication. The role is hybrid and based in the Boston or Las Vegas office, with required in-office days each week. Travel is expected for one to two weeks each quarter, primarily to Las Vegas and also to other domestic testing sites as business needs require. The estimated base salary range is $149,000–$198,500 USD. Additional compensation may include a bonus or company equity. Benefits may include medical, dental, vision, a 401(k) with company match, health savings accounts, life insurance, and pet insurance.

Requirements

Bachelor's degree in Engineering, such as Computer Science, Electrical, Systems, or Robotics, or equivalent work experience.
At least 5 years of professional software or systems engineering experience with safety-critical, complex systems such as autonomous vehicles, robotics, medical devices, or aerospace.
Thorough understanding of robotics systems, including sensors, actuators, and software autonomy stacks.
Strong proficiency in Python for data analysis and scripting, and a strong understanding of modern software development principles.
Ability to build data visualizations using Python frameworks.
Strong analytical and problem-solving skills for complex system performance evaluation.
Ability to reason logically, remove bias, perform root-cause analysis using system logs, and maintain a strict commitment to data quality and rigorous testing.
Proficiency with Git and standard version-control workflows.
Comfort working in a fast-paced, agile CI/CD environment.
Ability to work independently and effectively as part of a multidisciplinary team.
Excellent communication skills, including the ability to synthesize complex technical findings into clear summaries for cross-functional teams and executive leadership.
Ability to meet the physical demands described, including occasionally lifting and moving up to 50 pounds.

Nice To Haves

Master's degree.
Experience with AV-specific diagnostic and visualization tools, such as Planner Analyzer.
Knowledge of statistical analysis and machine learning techniques relevant to performance evaluation.
Willingness to learn business intelligence tools such as Looker.

Responsibilities

Investigate undesirable AV behaviors across simulation, hardware-in-the-loop (HIL), and on-road operations.
Own complex investigations from initial triage through resolution, working autonomously with little to no oversight.
Debug behaviors across perception, prediction, localization, planning, controls, and vehicle systems, including interactions between subsystems.
Analyze system logs, telemetry, and software outputs using Python.
Develop automated diagnostic workflows and internal tools using Python and Spaceship.
Build interactive dashboards using Python frameworks and business intelligence tools such as Looker to measure and report AV system performance.
Develop and test technical hypotheses from incomplete or ambiguous evidence, distinguishing symptoms from root causes.
Identify recurring undesirable behaviors, regressions, and emerging system-level performance issues, and categorize them into meaningful failure modes.
Translate technical investigations and performance metrics into clear summaries for executive reporting, release narratives, and cross-functional communication.
Travel to testing sites for one to two weeks each quarter, primarily to Las Vegas.