Neural Video Compression Research Scientist

Qualcomm; San Diego (CA); On-site; USD 158,400 - 237,600; Full time

Job summary

Qualcomm Technologies, Inc. in San Diego seeks a Video Compression Research Engineer focusing on learning-based video compression.

You will work within a world-renowned team to develop neural video coding technologies and contribute to future standards. The role involves contributing to conception, development, and optimization of neural compression algorithms, evaluating models with rate-distortion techniques, and engaging with standardization forums.

Qualifications

• PhD or Masters in Electrical Engineering, Computer Science, ML or related fields.
• Experience with learning-based video compression or neural compression research.
• Strong programming skills in Python/C++, with ML frameworks.

Responsibilities

• Contribute to conception, development, implementation, and optimization of learning-based video compression algorithms.
• Evaluate and improve neural and hybrid compression systems using state-of-the-art ML techniques and rate-distortion optimization.
• Represent Qualcomm in standardization forums (JVET, MPEG, ITU-T/VCEG) and contribute to publications.
• Document and present new algorithms and implementations through standards contributions and papers.

Skills

Neural video coding

Machine learning

Python

C/C++

PyTorch

Video coding standards

Rate-distortion optimization

Education

PhD

Master's degree

Bachelor's degree

Tools

Python

C/C++

PyTorch

Job description

Qualcomm Technologies, Inc. in San Diego seeks a Video Compression Research Engineer focusing on learning-based video compression.

You will work within a world-renowned team to develop neural video coding technologies and contribute to future standards. The role involves contributing to conception, development, and optimization of neural compression algorithms, evaluating models with rate-distortion techniques, and engaging with standardization forums.