Software Development · Santa Clara, CA

Full-time

Senior Software Development Engineer, Motion Planning - Autonomous Vehicles

NVIDIA · Santa Clara, CA · Posted Nov 14, 2026

This posting comes from NVIDIA. Confirm the details on their site before applying.

Overview

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.

Responsibilities

  • Lead motion planning features from initial design through productization and deployment.
  • Model L2, L3, and L4 vehicle behaviors and driving modes, using both optimal-control and classical behavior-planning methods.
  • Develop and integrate learned planning policies, including reinforcement learning and imitation learning, alongside optimization-based planners in the autonomous driving stack.
  • Build and maintain training pipelines and simulation environments, and benchmark learned policies against classical baselines in complex urban scenarios.
  • Optimize solvers and models for real-time deployment on automotive hardware.
  • BS or higher in Computer Science, Robotics, Electrical Engineering, or a related field (or equivalent experience).
  • 8+ years of relevant experience.
  • Proven ability to develop high-quality C++ and Python software for real-time systems within large, collaborative codebases.
  • Strong applied math background in linear algebra, numerical methods, and convex optimization.
  • Hands-on experience with machine learning in PyTorch, including RL methods such as PPO, GRPO, or actor-critic.

Preferred qualifications

  • Experience shipping autonomous driving features or embodied AI.
  • Expertise in constrained optimization-based trajectory generation and classical planners such as lattice-based planners, hybrid A*, or RRTs.
  • Background with generative policy or trajectory models such as Flow Matching, Diffusion, or AR-based decoders.
  • Experience training policies on their own rollout distributions and handling compounding error.
  • Experience with large-scale data flywheels: scenario mining from fleet logs, auto-labeling, and automated performance tracking.

Great fits start here.

Whether you're looking for your next role or your next team member, give people and possibilities a place to meet.