Research Intern - Multimodal AI for Robotic Vision

Varian Medical Systems, Inc.; United States; On-site; USD 48,000 - 75,000; Full time

Benefits offered by this job

medical insurance

dental insurance

vision insurance

401(k) retirement plan

life insurance

long-term and short-term disability

paid parking/public transportation

paid time off

paid sick and safe time

Job summary

Siemens Healthineers seeks a Research Intern to work on developing multimodal vision/language/action models for downstream robotic tasks. You will design pipelines that fuse multi-sensor imaging and kinematic signals into unified spatial representations, enabling perception to planning and control through VLA-based policies and AI decision-making frameworks.

The role targets highly motivated students or recent graduates pursuing advanced studies in Computer Science, Robotics, Electrical

Qualifications

• Currently enrolled in and pursuing studies at a foreign degree‑or‑certificate‑granting post‑secondary academic institution outside the United States OR has graduated from such an institution no more than 12 months prior to the exchange visitor program start date.

Responsibilities

• Developing and fine‑tuning multimodal vision/language/action models for downstream robotic tasks
• Designing pipelines that fuse multi-sensor imaging and kinematic signals into unified spatial representations
• Connecting perception to planning and control through VLA‑based policies and agentic AI decision‑making frameworks

Skills

Computer Vision

Deep Learning

Multimodal ML

Education

MS/PhD or postdoc in Computer Science/Robotics/Electrical/Biomedical Engineering

Tools

Python

PyTorch

Job description

Siemens Healthineers seeks a Research Intern to work on developing multimodal vision/language/action models for downstream robotic tasks. You will design pipelines that fuse multi-sensor imaging and kinematic signals into unified spatial representations, enabling perception to planning and control through VLA-based policies and AI decision-making frameworks.

The role targets highly motivated students or recent graduates pursuing advanced studies in Computer Science, Robotics, Electrical