Hedra is seeking a Research Scientist to lead innovation in video generation distillation, focusing on making state-of-the-art video diffusion models faster, lighter, and more deployable without sacrificing quality.
Requirements
- PhD or strong industry experience in Machine Learning, with a focus on model compression, distillation, or efficient deep learning.
- Strong understanding of diffusion models and their training/inference workflows.
- Proficiency in Python and PyTorch; familiarity with performance profiling and optimization.
- Experience with quantization, pruning, and low-rank adaptation techniques is a plus.
- A record of impactful work in model efficiency, either in research or production.
Responsibilities
- Research and develop distillation techniques for video diffusion models, including step distillation, layer pruning, and knowledge transfer.
- Optimize models for latency, memory footprint, and energy efficiency while maintaining high generation quality.
- Collaborate with engineering to implement and benchmark accelerated inference pipelines.
- Monitor and evaluate advancements in model compression, quantization, and efficient generative modeling.
- Present findings to the team and contribute to publications or patents where applicable.
Other
- We encourage you to apply even if you don't meet every requirement — we value curiosity, creativity, and the drive to solve hard problem
