ML Engineer / Researcher – Computer Vision (Generative Media)

Job Description:

ML Engineer / Researcher – Computer Vision (Generative Media)

Goal:

Make generative media go from idea to screen – put a creative studio in everyone’s hands.

You will:

• Build CV systems that generate minutes of studio-grade, coherent video (no flicker, no warping, no broken details).
• Turn pro editing tools into model controls: relighting, grading, matting, retiming, camera moves, typography – all inside the generator.
• Guarantee “ship-ready” output via quality signals and self-repair loops that catch and fix artifacts before delivery.
• Orchestrate multi-shot workflows (storyboard → shots → renders → revisions) with character/style continuity and asset memory across scenes.
• Serve at scale via distillation, quantization, streaming/progressive render, and multi-GPU orchestration with sub-second previews.
• Power the system with a data engine: curation, hard-case synthesis, preference learning – collaborating with artists to encode editorial taste.

Candidate Background:

• Broad knowledge of computer vision literature.
• Experience developing CV models for images and video.
• Deep expertise in generative models for video.