Doji
Research Engineer
New York City. Posted 18 months ago
The role
Research Engineers will build the next generation of avatar and virtual try-on models. You will implement generative AI features and build data pipelines for large-scale image and video datasets.
What you will do
- Implement cutting-edge generative AI features for inclusion in our product
- Build data pipelines to feed large-scale image and video datasets into model training
- Enhance model quality through user feedback and preference-based tuning
- Improve virtual try-on for diverse body types, clothing styles, and aesthetic treatments
- Collaborate effectively in a shared codebase while upholding high coding standards
- Develop state-of-the-art personalized try-on capabilities in video and 3D
- Work directly with our founders to create industry-leading technology
Required qualifications
- Hands-on experience training and fine-tuning diffusion models
- Familiarity with implementing and optimizing diffusion model training pipelines
- Worked in rigorous, fast-paced environments or been a very productive IC in academia or open-source
- Self-driven, high-agency, and can learn new things quickly and deeply
- Implemented ML papers from scratch in pytorch or jax
- Get excited about new ML methods, and read papers for fun
- Have instincts on how to get unstuck when things don't work
- Have genuine interest in fashion, avatars, or creative expression
Nice to have
- Experience with virtual try on
- Built consumer products
About the company
Doji is a small team of creative builders in NYC with a combination of taste and deep AI expertise. The company is backed by the investors behind OpenAI, Cursor, and SKIMS.