Senior Applied Scientist

What you'll do

• Design, implement, and evaluate mid-training approaches to improve editing capabilities for multimodal generative models.
• Own specific components of the mid-training stack such as image-to-image or instruction-based editing.
• Build and maintain large-scale captioning pipelines to enhance multimodal understanding across visual and auditory domains.
• Support VLM finetuning efforts to improve model performance in image, video, and audio tasks.
• Develop scalable workflows for data curation, quality improvements, and distributed training processes.
• Apply research insights from diffusion models and large-scale training to practical model improvements.
• Document experiments, datasets, and training approaches for cross-functional knowledge sharing.

What we're looking for

• Hold a Master’s or Ph.D. degree in Computer Science, Machine Learning, or a related field.
• Possess a solid understanding of modern generative architectures such as diffusion models.
• Demonstrate familiarity with conditional generation or editing methods for image, video, or audio tasks.
• Experience implementing machine learning models using PyTorch and other modern deep learning frameworks.
• Experience with large-scale or distributed training workflows is required.
• Possess a research background in VLM finetuning for multimodal understanding across visual and auditory domains.
• Familiarity with designing or applying automated captioning pipelines for large-scale data.
• Strong coding, prototyping skills in Python, and excellent communication skills are required.