Senior Software Engineer, AV Planner - Autonomous Vehicles

NVIDIA•Santa Clara, CA

8d•$224,000 - $356,500

About The Position

NVIDIA is seeking a Senior Software Engineer to develop, maintain, and integrate behavior and motion-planning algorithms and software for sophisticated urban autonomous driving. The role works on state-of-the-art autonomous vehicle technologies alongside teams in AI and deep learning, computer vision, mapping, prediction, and vehicle control, with a focus on planning for an L4 robotaxi. The engineer will design and build planning technologies and software modules that enable vehicles to operate safely and comfortably in dense urban environments. This includes behavior and trajectory planning, safety-oriented fallback behaviors, integration with other AV systems, and development of simulation, evaluation, and debugging tools. The position also supports cross-platform integration and on-vehicle issue resolution. The role calls for strong analytical, communication, and interpersonal skills, as well as the ability to collaborate across functions. Prior knowledge of L4 autonomy, safety-critical systems, real-time software, and large-scale evaluation is highly valued.

Requirements

BS, MS, or higher degree in Computer Science, Electrical Engineering, Robotics, Mechanical Engineering, or equivalent experience.
12+ years of experience in the relevant field.
Strong C/C++ software engineering skills, including production-quality, performance-aware, testable code.
Knowledge and hands-on background in several of the following: motion planning, decision-making, optimization, search, sampling-based planning, geometry, vehicle dynamics/kinematics, and real-time systems.
Experience building and using simulation and evaluation pipelines, writing unit and integration tests, and preventing regressions through automation.
Strong debugging skills across multi-module systems and ability to turn ambiguous on-road or simulation failures into actionable fixes.
Ability to communicate clearly and collaborate effectively across functions, including prediction, perception, controls, and safety.

Nice To Haves

Python experience for tooling and evaluation.
Hands-on experience shipping urban or L4 robotaxi planning (behavior and trajectory) with measurable improvements in safety and ride quality.
Experience with interaction-aware or uncertainty-aware planning, such as risk-sensitive decision-making, robust constraints, or prediction coupling.
Experience with automotive safety concepts and analysis methods, such as FMEA, and building credible validation strategies.
Track record of leading architecture or roadmap work and mentoring, or rapidly delivering high-quality features with strong engineering fundamentals.
PhD with relevant experience or significant industry experience in autonomy or robotics.

Responsibilities

Develop and ship behavior and trajectory planning for an L4 robotaxi, including lane changes, merges, intersections, unprotected turns, yielding, stop-and-go, and curbside operations.
Design planning technologies for the autonomous-vehicle software stack and write new software modules for safe, comfortable driving in dense urban environments.
Build optimization-, sampling-, or search-based planning approaches incorporating vehicle dynamics and constraints such as collision avoidance, comfort and jerk limits, and road-rule compliance.
Define and implement fallback and degraded-mode behaviors, such as safe stops and minimal-risk maneuvers, and contribute to safety-oriented design, including failure modes, redundancy, and validation evidence.
Integrate planning with prediction, perception, mapping/localization, and controls; define interfaces and troubleshoot end-to-end issues using logs and scenario replay.
Build and improve offline and closed-loop simulation benchmarks and metrics for planning quality, including safety, legality, comfort, and progress, and prevent regressions.
Define and build tools for debugging, scenario triage and mining, evaluation automation, and parameter and configuration management across vehicle platforms.
Drive integration across different platforms and vehicle types, and support reproduction and resolution of on-vehicle issues.