PhD Research Intern (Multimodal AI)

TL;DR

PhD Research Intern (Multimodal AI): Developing and training advanced multimodal AI architectures for spatial media content creation and generation with an accent on source separation and localization. Focus on prototyping algorithms, curating high-quality datasets, and contributing to scientific publications and patent applications.

Location: Must be based in San Francisco, California

Salary: $62/hr (approx. $9,920/month)

Company

hirify.global is a leader in entertainment innovation, pushing the boundaries of audio, imaging, and cloud technology to create spectacular experiences.

What you will do

• Develop and apply multimodal AI architectures integrating audio, visual, and language modalities.
• Design and train advanced models for spatial media content creation and source separation.
• Curate high-quality datasets using data augmentation and synthetic generation techniques.
• Evaluate proposed models against state-of-the-art research benchmarks.
• Prototype and validate developed algorithms in realistic use cases.
• Present research findings and contribute to patent applications and scientific publications.

Requirements

• Currently enrolled in a PhD program in Computer Science, Electrical Engineering, Applied Mathematics, or a related field.
• Strong background in deep learning applied to multimedia research.
• Deep familiarity with leading AI paradigms, including LLMs and generative models (diffusion, VAE, GAN).
• Proficiency in Python and at least one deep learning framework.
• Must be available to work full-time (Monday–Friday) for 12 weeks between September 2026 and December 2026.
• Strong mathematical foundation and excellent communication skills.

Culture & Benefits

• Opportunity to work within the Advanced Technology Group on cutting-edge research.
• Exposure to real-world applications of audio-visual AI technology.
• Collaborative environment focused on innovation and scientific contribution.
• Structured 12-week internship program with clear start dates.