About the role#
The Multimedia Lab develops video codec hardware solutions and explores research in video understanding, perceptual quality, and intelligent coding. You will work on projects that bridge the gap between research and production systems. Your work will influence the cost and quality of video across our products.
What you'll need#
- Currently pursuing a Master's degree in Computer Science, Electrical Engineering, Mathematics, Statistics, Data Science, or a related field.
- Strong fundamentals in algorithms, data structures, and software design.
- Familiarity with Python, PyTorch, and C/C++.
- Experience with token, image, or video coding and processing, or large multimodal models.
- A collaborative mindset and clear communication skills.
- Proficiency in deep learning frameworks like PyTorch, TensorFlow, and YOLO is preferred.
- Hands-on experience with LLMs and VLMs, including LoRA, diffusion models, and VQA tasks.
- Experience with model training, fine-tuning, and evaluation pipelines.
- Familiarity with GPU acceleration and CUDA configuration.
- Interest in video and image coding standards like H.266, AV1, or AVS3.
What you'll do#
- Design, develop, and optimize algorithms for data compression and large multimodal model applications.
- Work on 2D and multiview video, point clouds, neural-network-based coding, token compression, and KV cache optimization.
- Build prototypes and demonstrations to test new ideas.
- Keep up with current techniques by engaging in standardization activities or contributing to conference and journal publications.
- Write technical reports and contribute to patent filings.
Location & details#
- Location: San Diego, California.
- Modality: On-site.
- Employment: Full-time internship.
- Term: Rolling basis.


