Research Scientist

Velvet is a data research company focused on creating high-quality audiovisual training data for multimodal AI. They are seeking a Research Scientist to develop and fine-tune models for audio and video data processing, as well as conduct data-oriented research to enhance multimodal quality. Responsibilities: Research, develop, and fine-tune models for audio and video enhancement — including denoising, super-resolution, speech restoration, and perceptual quality improvement — ensuring outputs meet the standards required for frontier model training; Experiment with novel architectures, training objectives, and data augmentation strategies to improve model performance across diverse and noisy real-world audiovisual data; Build evaluation frameworks and benchmarks to rigorously measure enhancement quality, guiding iterative model improvement; Collaborate with infrastructure and data pipeline engineers to integrate trained models into large-scale processing workflows that handle wide variation in speech, visual quality, and format Qualifications: Strong research background in deep learning, with hands-on experience training and fine-tuning models for audio processing, video processing, or related domains; Proficiency in PyTorch; Experience designing and running experiments at scale; Solid understanding of signal processing fundamentals and how they inform model design for enhancement tasks; A publication track record or demonstrated research output in relevant areas (audio/speech enhancement, video restoration, generative models, multimodal learning); Ability to work effectively in an early-stage environment where scope is broad and priorities shift fast Required Skills: Deep learning, Model training, Fine-tuning, Audio processing, Video processing, PyTorch, Experiment design, Execution, Signal processing fundamentals, Research publication, Output, Multimodal learning, Generative models, Diffusion models, Autoencoders, Transformer architectures, Perceptual quality metrics, Human evaluation methodologies, Work effectively in a fast-changing environment