AI Engineer, World Modeling & Video Generation, Tesla AI - Palo Alto [255816]

$176,000 - $420,000 yearly

Job Description

Video generation models have made significant progress recently but continue to struggle with respecting physics, causality, and fine controllability. At Tesla, we’re training world models on millions of hours of real-world action-conditioned video using one of the biggest compute clusters. Instead of generating more AI slop, our goal is to faithfully reproduce real-world successes and failures, on both the bot and car platform, for the purposes of evaluation and closed-loop reinforcement learning.

For more information, please watch this video.

The Role

  • Design and train action-conditioned video generation models that predict future frames and sensor states
  • Develop causal, physics-aware architectures that model interactions, motion, and environmental dynamics
  • Integrate 3D generative techniques such as Gaussian Splatting and volumetric rendering for high-fidelity realism
  • Implement closed-loop training systems where models iteratively refine predictions through feedback and simulation
  • Optimize distributed pipelines for large-scale multimodal training and real-time inference
  • Collaborate across Autonomy and Robotics to align model design, evaluation, and deployment

Requirements

  • Expertise in generative video or world model architectures
  • Strong background in spatiotemporal modeling, 3D scene understanding, or neural simulation
  • Proficiency with PyTorch or JAX
  • Experience in large-scale distributed training, especially the different forms of parallelism
  • Familiarity with reinforcement or imitation learning in simulated or embodied environments
  • Curiosity about building intelligent systems that understand and generate the world around them
Anthony Antonucci

Qualifications

Relevant experience in Tesla AI; strong problem-solving skills; commitment to Tesla mission.

Immediate Fill

No