Research Scientist, Video Generation Distillation
Job Description
About Hedra
Hedra is a pioneering generative media company backed by top investors at Index, A16Z, and Abstract Ventures. We're building Hedra Studio, a multimodal creation platform capable of control, emotion, and creative intelligence.
At the core of Hedra Studio is our Character-3 foundation model, the first omnimodal model in production. Character-3 jointly reasons across image, text, and audio for more intelligent video generation — it’s the next evolution of AI-driven content creation.
At Hedra, we’re a team of hard-working, passionate individuals seeking to fundamentally change content creation and build a generational company together. We value startup energy, initiative, and the ability to turn bold ideas into real products. Our team is fully in-person in SF/NY with a shared love for whiteboard problem-solving.
Overview
We are seeking a Research Scientist to lead innovation in video generation distillation, including step distillation, model size reduction, and efficient inference methods. This role focuses on making state-of-the-art video diffusion models faster, lighter, and more deployable without sacrificing quality. The ideal candidate will be experienced in model compression techniques and capable of bridging cutting-edge research with production needs.
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.
Qualifications
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.
Benefits
Competitive compensation + equity
401k (no match)
Healthcare (Silver PPO Medical, Vision, Dental)
Lunch and snacks at the office
We encourage you to apply even if you don't meet every requirement — we value curiosity, creativity, and the drive to solve hard problem
