Image Processing Intern
About The Position
Dolby Vision delivers a premium HDR experience across devices from large televisions to mobile screens. With the recent announcement of Dolby Vision 2, we're pushing picture quality and features to new heights. We're seeking an intern with machine learning expertise to help optimize the performance of our ML models used in Dolby Vision image processing pipelines. You'll investigate and implement approaches to improve inference speed and efficiency while maintaining model quality. This role offers hands-on experience with production ML systems in a world-class media technology environment.
Requirements
- Currently pursuing MS or PhD in Computer Science, Electrical Engineering, or related field
- Strong programming skills in C/C++ and Python
- Experience with machine learning frameworks and model optimization
- Strong analytical and problem-solving skills
Nice To Haves
- Experience with PyTorch, TensorFlow, or other ML training frameworks
- Familiarity with model optimization techniques
- Background in image/video processing or computer vision
- Coursework or projects involving AI for image/video applications
- Knowledge of HDR imaging or video processing pipelines
- Familiarity with ONNX
- Experience with performance profiling and optimization tools
Responsibilities
- Analyze and optimize existing ML models for improved inference performance
- Research and evaluate various optimization approaches suitable for our use cases
- Benchmark and compare model performance across different strategies
- Investigate opportunities for architectural improvements
- Collaborate with Dolby Vision engineering and research teams on real-world deployment challenges
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Intern
Number of Employees
1,001-5,000 employees
