Research Scientist (diffusion)

What you'll do

• Lead research and develop algorithms for text-to-video diffusion, improving visual quality, temporal consistency, and semantic fidelity.
• Design experiments, evaluate model performance, and collaborate to integrate research into production.
• Publish and contribute to open-source research, mentor junior researchers, and align research with product needs.

What they ask for

• Ph.D. in Computer Science, Artificial Intelligence, Machine Learning, or a closely related field.
• Strong publication record in top-tier conferences, focused on generative models, particularly diffusion models.
• Extensive experience implementing and optimizing large-scale generative models for image or video tasks; deep understanding of text-to-image and text-to-video generation.
• Proficiency in Python and PyTorch or TensorFlow; excellent communication and collaborative skills.

Nice to have

• Postdoctoral or industrial research experience in generative AI for video; hands-on text-to-video project experience.
• Experience with GANs or VAEs, large-scale datasets and distributed computing, product technology transfers, video codecs, compression, perceptual quality metrics, or open-source contributions.

Tools

Python, PyTorch, TensorFlow, GANs, VAEs

AI focus

Research and develop diffusion models and algorithms for text-to-video generation, with emphasis on visual quality, temporal consistency, and semantic fidelity.