Reinforcement Learning And World Model For Autonomous Driving Intern - 2026
Invidia
Multiple Locations
Hybrid
Model-centric reinforcement learning
Multi-modal world simulation models
Self-supervised latent dynamics training
This internship offers a rare opportunity to shape the next frontier of intelligent driving by building state-of-the-art simulation technologies that learn, adapt, and think
Job Summary
This internship offers a rare opportunity to shape the next frontier of intelligent driving by building state-of-the-art simulation technologies that learn, adapt, and think.
You will collaborate with End-to-End Driving Model teams to deploy world-model-based policies to simulated reinforcement learning environments and accelerate autonomous driving system training.
The role focuses on translating state-of-the-art algorithms into real-world applications to enable vehicles to interpret, anticipate, and respond astutely in challenging dynamic contexts.
Matching Summary
This internship offers a rare opportunity to shape the next frontier of intelligent driving by building state-of-the-art simulation technologies that learn, adapt, and think.
Skills & Requirements
Must-have
Model-centric reinforcement learning
Multi-modal world simulation models
Self-supervised latent dynamics training
Trajectory prediction and ego control
Simulation adaptation and Sim2Real transfer
Policy gradient methods
Large-scale training pipelines
Nice-to-have
Neural rendering and robotics background
Generative models like diffusion and flow matching
Visual representation learning
4D scene representation techniques
Open-source contributions
Collaborative team environment
Key Requirements
Pursuing PhD in Computer Science or related field
Strong understanding of reinforcement learning algorithms
Experience with neural rendering or robotics
Publications or open-source contributions in RL or autonomous systems