2027 Summer Intern, Machine Learning, MS/PhD, Simulation Realism (World Model)

Skills

About the Role

You will implement, train, and evaluate generative models such as diffusion models, flow matching, or autoregressive transformers for video and physical world simulation. You will experiment with unified 3D/4D and spatiotemporal representations, investigate conditioning, fine-tuning, and distillation methods to improve temporal consistency, physical realism, and inference speed, and partner with mentors and researchers to translate research prototypes into the simulation pipeline.

Requirements

• Currently pursuing an MS or PhD in Computer Science, Machine Learning, Computer Vision, Robotics, or a related field
• Solid background in deep learning and computer vision, with hands-on experience in modern generative modeling
• Strong coding skills in Python and practical experience training and debugging models in PyTorch or JAX

Responsibilities

• Implement, train, and evaluate generative models (diffusion models, flow matching, autoregressive transformers) for video and physical world simulation
• Experiment with unified 3D/4D and spatiotemporal representations across diverse scenes, vehicle platforms, and sensor modalities
• Investigate conditioning, fine-tuning, or distillation methods to improve temporal consistency, physical realism, and inference speed for closed-loop simulation
• Partner with mentors and researchers to adapt foundation world models and translate research prototypes into the simulation pipeline

Benefits

• Medical, dental and vision insurance
• Mental wellness support
• Gym membership and wellness programs
• Bonus opportunities
• Equity
• Paid time off, bereavement, sick, and parental leave
• Work from another location four weeks per year
• 26 weeks paid leave for birthing parents and 18 weeks for non-birthing parents
• Education reimbursement
• Access to Google offices, cafes, wellness centers