Multimodal Audio-Video Enhancement Scientist

Velvet; San Francisco (CA); On-site; USD 110,000 - 150,000; Full time

Job summary

A data research company in San Francisco seeks a Research Scientist to develop and enhance models for audiovisual data processing. This role involves researching novel methods for audio and video enhancement, running large-scale experiments, and collaborating with engineers for workflow integration. Ideal candidates have a strong background in deep learning, proficiency in PyTorch, and familiarity with signal processing. The environment is fast-paced, rewarding impactful applied research efforts.

Qualifications

• Experience training models for audio or video processing.
• Solid understanding of signal processing fundamentals.
• Ability to run experiments at scale.

Responsibilities

• Research and develop models for audio and video enhancement.
• Experiment with architectures and data augmentation.
• Build evaluation frameworks to measure model performance.
• Collaborate with engineers for model integration.

Skills

Deep learning research background

Proficiency in PyTorch

Experience in signal processing

Publication track record

Ability to adapt in early-stage environments

Job description

A data research company in San Francisco seeks a Research Scientist to develop and enhance models for audiovisual data processing. This role involves researching novel methods for audio and video enhancement, running large-scale experiments, and collaborating with engineers for workflow integration. Ideal candidates have a strong background in deep learning, proficiency in PyTorch, and familiarity with signal processing. The environment is fast-paced, rewarding impactful applied research efforts.