Midjourney is looking for a Generative Art Researcher to push the boundaries of AI image generation. You will develop new architectures and techniques for high-fidelity image synthesis, style transfer, and creative control in AI art generation.
Requirements
- PhD or equivalent experience in computer vision or generative models
- Strong expertise in diffusion models and image synthesis
- Deep proficiency in PyTorch
- Publications in top computer vision or ML venues
- Artistic sensibility and understanding of visual aesthetics
Nice to Have
- Experience with text-to-image generation at scale
- Background in art, design, or photography
- Experience with ControlNet or image editing models
- Familiarity with 3D-aware image generation
Small team, high impact
Remote-first culture
Hardware budget
#J-18808-Ljbffr