Your personal AI career agent
Internship Multimodal AI for Video Understanding(m/w/x)
Developing multimodal AI models for holistic video understanding using real-world ZEISS datasets. Experience with video analysis, multimodal learning, or foundation models a plus. Access to challenging datasets and modern ML infrastructure.
Requirements
- Enrolled in Master’s/PhD in Computer Science/ML
- Strong machine learning/deep learning fundamentals
- Python and ML frameworks experience
- Research interest and independent work ability
- Video analysis, multimodal learning, or foundation models experience (plus)
Tasks
- Conduct research on multimodal and video-based machine learning
- Develop models for holistic video understanding
- Evaluate video-language models and temporal reasoning techniques
- Integrate multimodal fusion methods
- Work with real-world datasets from ZEISS applications
- Implement and analyze state-of-the-art approaches
- Extend existing methods in a research-driven setting
- Focus on complex real-world scenarios like surgical workflows
- Move beyond frame-level analysis to holistic, temporally consistent representations
Education
- Currently in higher education
Languages
- English – Business Fluent
Tools & Technologies
- Python
- PyTorch
Benefits
Diverse Work
- Access to challenging datasets
Modern Equipment
- Modern ML infrastructure
Like this job?
BetaYour Career Agent finds similar jobs for you every day.
Not a perfect match?
- BMW GroupFull-timeInternshipOn-siteMünchen
- BMW Group
Intern LLM-enhanced in-vehicle personal assistants(m/w/x)
Full-timeInternshipOn-siteMünchen - Airbus Defence and Space GmbH
Internship in Neuromorphic Computer Vision(m/w/x)
Full-timeInternshipOn-siteMünchen - Analog Devices, Inc.
RF & Edge AI Intern(m/w/x)
Full-timeInternshipOn-siteMünchen - Helsing
AI Working Student - Computer Vision(m/w/x)
Full-timeWorking StudentOn-siteMünchen
Internship Multimodal AI for Video Understanding(m/w/x)
Developing multimodal AI models for holistic video understanding using real-world ZEISS datasets. Experience with video analysis, multimodal learning, or foundation models a plus. Access to challenging datasets and modern ML infrastructure.
Requirements
- Enrolled in Master’s/PhD in Computer Science/ML
- Strong machine learning/deep learning fundamentals
- Python and ML frameworks experience
- Research interest and independent work ability
- Video analysis, multimodal learning, or foundation models experience (plus)
Tasks
- Conduct research on multimodal and video-based machine learning
- Develop models for holistic video understanding
- Evaluate video-language models and temporal reasoning techniques
- Integrate multimodal fusion methods
- Work with real-world datasets from ZEISS applications
- Implement and analyze state-of-the-art approaches
- Extend existing methods in a research-driven setting
- Focus on complex real-world scenarios like surgical workflows
- Move beyond frame-level analysis to holistic, temporally consistent representations
Education
- Currently in higher education
Languages
- English – Business Fluent
Tools & Technologies
- Python
- PyTorch
Benefits
Diverse Work
- Access to challenging datasets
Modern Equipment
- Modern ML infrastructure
Like this job?
BetaYour Career Agent finds similar jobs for you every day.
About the Company
Carl Zeiss AG
Industry
IT
Description
Das Unternehmen vereint Innovation und Verantwortung und trägt entscheidend zur strategischen Ausrichtung und zum nachhaltigen Erfolg der ZEISS Gruppe bei.
Not a perfect match?
- BMW Group
Intern Multimodal Agentic AI for In-car Voice Assistant(m/w/x)
Full-timeInternshipOn-siteMünchen - BMW Group
Intern LLM-enhanced in-vehicle personal assistants(m/w/x)
Full-timeInternshipOn-siteMünchen - Airbus Defence and Space GmbH
Internship in Neuromorphic Computer Vision(m/w/x)
Full-timeInternshipOn-siteMünchen - Analog Devices, Inc.
RF & Edge AI Intern(m/w/x)
Full-timeInternshipOn-siteMünchen - Helsing
AI Working Student - Computer Vision(m/w/x)
Full-timeWorking StudentOn-siteMünchen