AI Research Intern, TAO Multi-Modal Model Development - 2026
Core
Extending an internship to develop and fine-tune multi-modal AI models, specifically vision-language models and universal segmentation systems, using NVIDIA's TAO framework.
Role type
AI Research Intern (Multi-Modal Model Development)
Builds
Scalable, high-impact AI solutions including vision-language models and universal segmentation systems.
Domain
Artificial Intelligence, Deep Learning, Computer Vision
Deliverable
production ML models
Required skills
Python, PyTorch, neural network architectures, transformers, multi-modal learning techniques, model fine-tuning, experiment design, benchmarking
Preferred skills
vision-language models, image segmentation, large-scale pretraining
Responsibilities
Develop and fine-tune multi-modal AI models using TAO Toolkit; Contribute to design and implementation of VLMs and segmentation systems; Conduct experiments and benchmarking; Collaborate on integrating research into production pipelines; Participate in research discussions and code reviews
Seniority
Intern
