We build generative AI software for image and video enhancement. Over 1M photographers and designers trust us with their work, including on teams at Apple, Netflix, NASA, and more. Over the past few years we've processed over 1 billion images, grown extremely quickly, and we're just getting started.
We're looking for a Generative AI researcher to help us produce best-in-the-world performance and efficiency in image/video enhancement and editing. Your primary responsibility will be to explore and develop GAN and diffusion-based generative AI technologies in the image and video domain. Experience with model distillation, quantization, and pruning to improve inference and memory efficiency while retaining performance is highly desirable.
About us
- Rocketship growth and opportunity for impact ($3M → $45M revenue in five years)
- Over 1 million customers (including companies like Apple, NASA, Netflix) have used us for over 1 billion photos. Our tech has been covered by Fast Company, The Verge, Engadget, Mashable, BBC, Fox News, CNet, and more
- World-class team that executes quickly, obsesses about the customer experience, and promotes from within
- Fast-growing with huge opportunity for impact
- Strong product-market fit, profitable with infinite runway
About you
- PhD in related field or equivalent industry experience
- Significant research on GAN or diffusion models for image/video enhancement, image processing, or image editing
- Experience with model distillation, quantization, and pruning
- 2+ years of hands-on experience with PyTorch, expert level at python
- Working knowledge of C/C++
- Well-read on recent relevant research papers
- Preferred: experience with traditional image/video processing and photography interest