Vision-Language-Action (VLA) Research Intern

Quick Facts

• Role: Vision-Language-Action (VLA) Research Intern

• Focus: ADAS/AD research using world-action models, generative modeling, and world models

Description

You will contribute to research for autonomous driving by combining VLA with generative modeling and world models to move toward scalable autonomy. Responsibilities include designing and training world-action models conditioned on ego actions, integrating world models with end-to-end or model-based driving policies, and summarizing results in papers and/or patent submissions.

Responsibilities

• Design and train world-action models (autoregressive or diffusion-based) to predict future sensor observations or latent states conditioned on ego actions

• Integrate world models with planning for end-to-end or model-based driving policies

• Summarize research findings in high-quality papers and/or patent submissions

• Collaborate with other researchers to drive top-venue publications and/or product impact

Requirements

• Currently enrolled Ph.D. student in Computer Science, Robotics, Computer Engineering, or a related field

• Minimum GPA of 3.0

• Hands-on experience with at least one of: generative models (diffusion, autoregressive transformers, VAEs), world models/video prediction, or end-to-end autonomous driving

• Solid deep learning fine-tuning skills and proficiency with deep learning frameworks

• Experience with reinforcement learning and/or model-based planning

Benefits

• Equal Opportunity Employer

• Drug screen and background check required

• STEM-focused culture and support (STEM, FIRST Robotics, AWIM)

• U.S. base salary range: $60.00–$70.00 per hour (intern position); determined by degree type, work experience, and job-related factors