NVIDIA is seeking a Senior Deep Reinforcement Learning Engineer to join their autonomous driving team. The successful candidate will work on building and implementing new Reinforcement Learning (RL) algorithms for autonomous vehicle decision-making and planning.
Responsibilities:
- Build and implement brand new Reinforcement Learning (RL) algorithms for autonomous vehicle decision-making and planning.
- Develop and maintain scalable training pipelines and simulation environments for RL training.
- Collaborate with perception and planning teams to integrate RL models into the unified autonomous driving stack.
- Benchmark RL model performance against imitation learning baselines in complex urban environments.
- Optimize and deploy RL models to production-grade automotive hardware.
Requirements:
- BS or higher in Computer Science, Robotics, Electrical Engineering, or a related field (or equivalent experience).
- 12+ years of experience in the related field.
- Solid background in Reinforcement Learning, including policy gradient methods (PPO, GRPO), actor-critic architectures, on-policy and off-policy RL.
- Proficiency in PyTorch or TensorFlow and real experience with RL-related algorithms.
- Experience in C++ and Python development for real-time systems.
- Strong analytical and problem-solving skills, with a track record of implementing and debugging complex RL systems.
Nice to Have:
- Background in shipping autonomous driving features or embodied AI.
- Experience with generative models (Flow Matching, Diffusion, or AR-based decoders) in the context of policy representation or trajectory modeling.
- Experience with training policies on their own rollout distributions and handling the compounding error problems inherent in autonomous driving.
- Experience working with large-scale data flywheels, including mining scenarios from fleet telemetry logs, auto-labeling pipelines, and automated performance tracking.
Benefits:
- Equity
- Benefits
