Vision‑Language‑Action (VLA) Research Intern

Bosch Group • Sunnyvale, CA

1d

About The Position

As a Research Intern for World-Action Models / VLA for Autonomous Driving, you will contribute to research projects in the ADAS/AD industry. The role focuses on the intersection of vision-language-action models, generative modeling, and world models, with research aimed at scalable autonomy. You will collaborate closely with other researchers; strong work is expected to contribute to top-venue publications and/or product impact.

Requirements

• Be a currently enrolled Ph.D. student in Computer Science, Robotics, Computer Engineering, or a related field.
• Have a minimum GPA of 3.0.
• Have hands-on experience with at least one of the following: generative models (diffusion, autoregressive transformers, or VAEs), world models or video prediction, or end-to-end autonomous driving.
• Have solid fine-tuning skills and proficiency with deep learning frameworks.
• Have experience with reinforcement learning and/or model-based planning.

Nice To Haves

• Publication record in top venues, including CVPR, ICCV, ECCV, ICLR, NeurIPS, and ICML.
• Familiarity with driving benchmarks such as NavSim and Bench2Drive.
• Experience with large-scale distributed training and multi-modal or video data pipelines.
• Ability to work independently, with strong research and problem-solving skills.
• Good communication and teamwork skills.

Responsibilities

• Design and train world-action models, including autoregressive or diffusion-based models, that 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 paper and/or patent submissions.
• Collaborate closely with other researchers.

What This Job Offers

• Job Type: Full-time
• Career Level: Intern
• Education Level: Ph.D. or professional degree