Research Scientist / Engineer - Video Generative AI

Decart; Deutschland; Remote; EUR 70.000 - 100.000; Vollzeit

Zusammenfassung

A leading AI tech company in Germany is seeking a Video Generative AI Research Scientist/Engineer to advance their innovative AI interactive video technologies. The ideal candidate has a PhD in Computer Science or related fields and experience in training generative models. Responsibilities include designing models for video, optimizing inference infrastructure, and collaborating across teams to launch products. This role offers significant growth potential.

Qualifikationen

• Strong hands-on background in training generative models.
• Comfort with designing and training state-of-the-art models.
• Proven ability to transition ideas from research to production.

Aufgaben

• Design and train state-of-the-art generative models for video.
• Develop and optimize infrastructure for fast inference.
• Collaborate across research and engineering teams.
• Contribute to the overall research agenda.

Kenntnisse

Training generative models

Model design and training

Multimodal data experience

Ausbildung

PhD in Computer Science or related field

MSc with equivalent industry research experience

Jobbeschreibung

Overview

Decart is seeking a Video Generative AI Research Scientist / Engineer to be a foundational part of our US team, driving the evolution of our cutting-edge AI interactive video technologies. This role is crucial as we are poised for rapid growth with strong backing from top-tier investors like Sequoia and Benchmark.

Qualifications

What we’re looking for: Someone with a PhD in Computer Science, Electrical Engineering, or a related field, or an MSc with equivalent industry research experience. You should have a strong, hands-on background in training generative models (like diffusion or rectified flow). Comfort with designing and training state-of-the-art models is a must, along with a proven ability to transition ideas from research to production. Bonus points for experience with multimodal (video / audio) data or real-time systems.

Responsibilities

• Design and train state-of-the-art generative models (diffusion, rectified flow, etc.) for video.
• Develop and optimize our proprietary infrastructure for fast inference and rapid training at scale.
• Collaborate across research and engineering to prototype and ship interactive user experiences, closing the loop from idea to live product.
• Contribute to the overall research agenda and help shape the future of human–pixel interaction.