PhD Research Intern - Foundational AI (Fall 2026, Atlanta)

While traditional focus on foundation models has centered around standard audio and visual technologies, Dolby is pioneering the application of these powerful AI systems to enhance media experiences. We are seeking a PhD research intern to join our Foundational AI lab to explore how large-scale models can be leveraged for spatial audio, HDR imaging/video, and high pixel depth imaging/video generation and representation learning. 

As a Research Intern, you will: 

• Design and implement novel neural architectures for processing enhanced media formats. 

• Develop training methodologies for foundation models that can understand and generate high-fidelity audio-visual content. 

• Research techniques for efficient fine-tuning of large models for Dolby-specific applications. 

• Collaborate with cross-functional teams to integrate research findings into Dolby's product ecosystem. 

• Present research findings to internal stakeholders and potentially at academic conferences. 

The role will be based out of our research facility in Atlanta, GA, and offers the opportunity to work with state-of-the-art computing resources and proprietary datasets. 

Requirements 

• Currently enrolled in a PhD program in Computer Science, Electrical Engineering, Machine Learning, Computational Media, or related fields. 

• Strong background in imaging/video/audio modeling and understanding. 

• Demonstrable proficiency in training and fine-tuning large models (diffusion models, transformers, autoregressive models, etc.). 

• Solid understanding of deep learning fundamentals and experience with frameworks such as PyTorch. 

• Excellent programming skills in Python. 

• Ability to work independently and as part of a collaborative research team. 

Desirable Experience 

• First-authored publication in relevant domains at top conferences such as CVPR, ICCV, NeurIPS, ICLR, ICML, ICASSP, and similar venues. 

• Experience with scaling up model training across multiple GPUs across hybrid infrastructures. 

• Familiarity with audio processing, computer vision, or multimedia systems. 

• Knowledge of perceptual quality metrics for audio and visual media. 

• Prior work with HDR imaging or spatial audio technologies. 

Application Process 

We will review applications on a rolling basis. Qualified candidates should submit a CV, research statement, and relevant publications or project examples. For the best chance to have your resume reviewed and considered, we recommend submitting your application by June 26, 2026.  

Join us in shaping the future of entertainment technology through the power of AI and foundation models. 

Eligibility 

Currently enrolled in Doctoral program. Must be available to work full-time Monday – Friday for 12 weeks between September 2026 – December 2026.  

The start date for this internship is as follows (please note these dates are not flexible):  

• September 21, 2026