Machine Learning Researcher

Job Title: ML Engineer / Researcher – Computer Vision (Generative Media)

Location:
Manhattan, NY (Onsite / Hybrid)

Job Type: Full-time

About the role

• Build the engine behind next-generation generative video.
• We’re building systems that turn ideas into studio-grade video instantly. Our mission is to put a creative studio in everyone’s hands by developing cutting-edge generative media technology that delivers cinematic, coherent, production-ready output.
• We’re looking for a world-class ML Engineer / Researcher specializing in computer vision and generative video to help us redefine how video is created.

What You’ll Do

• Develop computer vision systems capable of generating minutes of temporally coherent, studio-grade video no flicker, no warping, no broken details.
• Build quality signals and automated self-repair loops that detect and fix artifacts before delivery.
• Design multi-shot generative workflows (storyboard → shots → renders → revisions) with strong character/style continuity across scenes.
• Optimize systems for scale using:
• Multi-GPU orchestration
• Sub-second preview systems
• Develop and power a robust data engine:
• Dataset curation
• Hard-case synthesis
• Preference learning
• Collaboration with artists to encode editorial taste

What We’re Looking For

• Deep understanding of computer vision research and literature
• Hands-on experience building CV models for images and video
• Experience in training and scaling large ML systems
• Strong Python skills and proficiency with PyTorch (or similar frameworks)
• Passion for pushing the limits of generative AI

Bonus Points

• Research publications in computer vision or generative modeling
• Experience building production ML systems
• Familiarity with video pipelines or creative tools
• Background working closely with creative teams