Research Scientist, Long Video Generation jobs in United States
info-icon
This job has closed.
company-logo

Hedra · 5 months ago

Research Scientist, Long Video Generation

Hedra is a pioneering generative media company focused on building innovative solutions for content creation. They are seeking a highly motivated Research Scientist to advance long-form video generation through auto-regressive modeling and causal attention mechanisms, while integrating research into production-grade pipelines.

Artificial Intelligence (AI)ContentMedia and EntertainmentVideo

Responsibilities

Design and implement long video generation architectures, with emphasis on auto-regressive generation, causal attention, and memory-efficient transformer designs
Develop methods for maintaining temporal and semantic coherence over long time horizons
Work closely with engineering to integrate research into production-grade pipelines
Stay on top of recent advances in long-context transformers, sequence compression, and scalable video generation
Present results internally and externally, including possible top-tier conference submissions

Qualification

In Computer ScienceMachine LearningTransformer architecturesAuto-regressive modelingPythonPyTorchCausal attention mechanismsLong-context processingMemory-efficient computationImpactful research

Required

PhD or strong research/industry experience in Computer Science, Machine Learning, or related fields, with a focus on sequence modeling or generative models
Deep understanding of transformer architectures, attention mechanisms, and auto-regressive modeling
Experience with long-context processing and memory-efficient computation
Proficiency in Python and PyTorch; ability to rapidly prototype and iterate on new architectures
A record of impactful research or large-scale system deployments

Benefits

Competitive compensation + equity
401k (no match)
Healthcare (Silver PPO Medical, Vision, Dental)
Lunch and snacks at the office

Company

Hedra

twittertwittertwitter
company-logo
Hedra is a content creation platform that uses AI to enables users to generate videos, images, and audio.

Funding

Current Stage
Early Stage
Total Funding
$43M
Key Investors
Amazon Web ServicesAndreessen Horowitz
2025-10-08Non Equity Assistance· $1M
2025-05-15Series A· $32M
2024-08-01Seed· $10M
Company data provided by crunchbase