Senior Software Engineer, AV Planner - Autonomous Vehicles
NVIDIA
- Location
- US, CA, Santa Clara
- Work model
- On-Site
- Level
- Senior
- H-1B history
- 394 approvals (FY2023)
- Posted
- Aug 27, 2026
Skills
About this role
NVIDIA has been transforming computer graphics, PC gaming, and accelerated computing for more than 25 years. It’s a unique legacy of innovation that’s fueled by great technology—and amazing people. Today, we’re tapping into the unlimited potential of AI to define the next era of computing. An era in which our GPU acts as the brains of computers, robots, and self-driving cars that can understand the world. Doing what’s never been done before takes vision, innovation, and the world’s best talent. As an NVIDIAN, you’ll be immersed in a diverse, supportive environment where everyone is inspired to do their best work. Come join the team and see how you can make a lasting impact on the world. We are looking for a Senior Software Engineer, AV Planner. As an AV Planning Engineer, you will work on state-of-the-art autonomous vehicle technologies with leaders in AI / deep learning, computer vision, mapping, prediction, and vehicle control. You will be responsible for developing, maintaining, and integrating behavior and motion planning algorithms and software for sophisticated urban driving. You should have strong analytical skills, good communication, and interpersonal capabilities to work in a team and make a joint effort towards a common goal. Prior knowledge of L4 autonomy, safety-critical systems, real-time software, and large-scale evaluation is highly valued. What you’ll be doing: Develop and ship behavior and trajectory planning for an L4 robotaxi (lane changes, merges, intersections, unprotected turns, yielding, stop-and-go, curbside operations). Design planning technologies needed to build the AV software stack; write new software modules from scratch that drive vehicles safely and comfortably in dense urban environments. Build optimization-, sampling-, and/or search-based planning approaches with vehicle dynamics and constraints (collision avoidance, comfort/jerk limits, road-rule compliance). Define and implement fallback and degraded-mode behaviors (e.g., safe stop / minimal risk maneuvers) and contribute to safety-oriented design (failure modes, redundancy, validation evidence). Integrate planning with prediction, perception, mapping/localization, and controls; define clean interfaces and troubleshoot end-to-end system issues using logs and scenario replay. Build and improve offline and closed-loop simulation benchmarks and metrics for planning quality (safety, legality, comfort, progress), and drive regression prevention. Define and build tools to accelerate debugging, scenario triage/mining, evaluation automation, and parameter/config management across vehicle platforms. Drive integration efforts across different platforms/vehicle types; support on-vehicle issue reproduction and resolution. Most importantly, work on groundbreaking and innovative technology, tackle difficult problems, and help build a world-class system! What we need to see: BS, MS, or higher degree in Computer Science, Electrical Engineering, Robotics, Mechanical Engineering, or equivalent experience. 12+ years of expereince in the relevant field. Strong software engineering skills in C/C++ (production-quality, performance-aware, testable code); Python experience for tooling/evaluation is a plus. Knowledge and hands-on background in several of the following: motion planning, decision-making, optimization, search, sampling-based planning, geometry, vehicle dynamics/kinematics, real-time systems. Experience building and using simulation and evaluation pipelines, writing unit/integration tests, and preventing regressions via automation. Strong debugging skills across multi-module systems; ability to turn ambiguous on-road/sim failures into actionable fixes. Ability to communicate clearly and collaborate effectively across functions (prediction/perception/controls/safety). Ways to stand out from the crowd: Hands-on experience shipping urban/L4 robotaxi planning (behavior + trajectory) with measurable improvements in safety