About the role
Advance the frontier of multimodal video generation at Mirage.
- •Mirage is seeking a Research Scientist to advance the frontier of multimodal video generation.
- •You'll work on novel modeling approaches, training objectives, and scaling strategies for large-scale video models, contributing directly to systems used by millions of creators.
- •Key Responsibilities Develop novel approaches to video and multimodal generative modeling Design new training objectives, loss functions, and evaluation methods optimizing for highly compute-efficient, low-latency generation Explore temporal modeling, controllability, and multimodal alignment Requirements MS/PhD in ML, CS, or related field Strong publication record (NeurIPS, ICML, ICLR, etc. or equivalent work) Deep expertise in generative modeling (diffusion, autoregressive architectures, etc.)
Tech stack
TensorFlowPyTorchscikit-learnHugging FaceComputer VisionNLPLLMs
Match insights
Tech:TensorFlow, PyTorch, scikit-learn, Hugging Face, Computer Vision
Level:Senior