Research Scientist, Long Video Generation Job at Hedra in San Francisco

Research Scientist, Long Video Generation 2 weeks ago • Be among the first 25 applicants Get AI-powered advice on this job and more exclusive features. 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 highly motivated Research Scientist to push the limits of long‑form video generation, focusing on auto‑regressive modeling, causal attention mechanisms, and efficient sequence handling. The ideal candidate will have a deep understanding of temporal modeling in generative AI and experience building scalable architectures for multi‑minute coherent video outputs. 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. Qualifications 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 We encourage you to apply even if you don’t meet every requirement — we value curiosity, creativity, and the drive to solve hard problems. #J-18808-Ljbffr In Summary: Research Scientist, Long Video Generation, will push the limits of long‑form video generation . The ideal candidate will have a deep understanding of temporal modeling in generative AI . Hedra Studio is a multimodal creation platform capable of control, emotion, and creative intelligence . En Español: Científico de Investigación, Long Video Generation hace 2 semanas • Estar entre los primeros 25 solicitantes Obtenga asesoramiento basado en la IA sobre este trabajo y características más exclusivas. Sobre Hedra Hedra es una empresa pionera de medios generativos respaldada por principales inversores de Index, A16Z y Abstract Ventures. Estamos construyendo Hedra Studio, una plataforma de creación multimodal capaz de controlar, emocionar e inteligencia creativa. En el núcleo del estudio Hedra se encuentra nuestro modelo fundacional Character‐3, el primer modelo omnimodal en producción. Responsabilidades Diseñar e implementar arquitecturas de generación de videos largos, con énfasis en la generación automática regresiva, atención causal y diseños de transformadores eficientes en memoria. Desarrollar métodos para mantener la coherencia temporal y semántica durante largos horizontes de tiempo. Trabajar estrechamente con la ingeniería para integrar la investigación a las tuberías de producción. Mantenerse al tanto de los avances recientes en transformadores de contexto largo, compresión de secuencias y generación escalable de video. Presentar resultados internamente y externamente, incluidas posibles presentaciones de conferencias de primer nivel. Calificaciones doctoradas o una sólida experiencia en investigación / industria en Ciencias de la Computación, Aprendizaje Automático o campos relacionados, con un enfoque en el modelado de secuencia o modelos generativos. Comprensión profunda de las arquitectura computacionales del transformer, mecanismos de atención y modelada auto-regresivista. Experiencia con iteración de contenido prolongado y memoria 401 . Proficiencia en Python y PYT; Proporciones médicas que permitan cumplir con todos los requisitos básicos del sistema, incluso si se aplican a las nuevas aplicaciones (LJ-180, LJ-18):