Software Engineer (Onboard Maps and State Estimation)

Join our Localization, Calibration, and Mapping team as a Software Engineer. You'll own the onboard live-map estimator, build our onboard map change detection, define map trust contracts, and ship estimation code in modern C++. This is a unique opportunity to set the architecture and define interfaces for a core system leveraged across the entire organization. Enjoy benefits such as 100% health insurance coverage, a fitness stipend, 401(k) match, learning stipend, parental leave, and catered meals.

• Own the onboard live-map estimator end to end, fusing HD map priors with live perception into a real-time estimate of the world.
• Build the onboard map change detection system, classifying situations like boundary shifts and defining when the planner should stop trusting the map.
• Define the map trust contracts the planner builds against, including confidence semantics, degraded-mode behavior, and operating points across vehicle programs.

• Rigorous evaluation practice: has built ground-truth or metrics pipelines and used them to hold a shipped operating point and prevent regressions
• 5+ years building production software, including at least one shipped system where they owned the estimation core
• Experience defining a system and its interfaces and negotiating those contracts with consumer teams
• Experience fusing heterogeneous sources such as prior map data, perception output, and raw sensors, into a single world estimate, with rigorous error characterization
• State estimation fundamentals proven in production: factor graphs and/or filtering, data association, uncertainty representation and propagation, and 3D geometry and transforms
• Strong modern C++ and the ability to make estimation code meet real-time budgets on embedded compute
• Judgment about uncertainty: understands the difference between an error that degrades gracefully and one that is catastrophic, and designs the system accordingly
• Map change detection or live/lifelong mapping experience
• HD map semantics: lane graphs, topology, map formats and their failure modes
• GTSAM or comparable factor-graph frameworks; Lie group methods
• Degraded-mode or integrity-monitor design for a safety-relevant function
• MS/PhD with a focus on state estimation or SLAM