Requirements:

• Comfortable owning and executing on responsibilities
• Strong ML and computer vision background
• Hands-on experience with diffusion models
• Proficient in PyTorch and modern ML frameworks
• Strong Python engineering skills and commitment to clean code
• Outcome-driven, detail-oriented, motivated researcher
• Clear communicator of hypotheses, experiments, results

Nice to Haves:

• Experience with audio-conditioned video diffusion models
• Demonstrated ability to own full model development pipeline
• Strong publication record in world models, interactive agents, or video diffusion models

What You'll Be Doing:

• Adapt diffusion models with diverse conditioning signals
• Develop methods for streaming infinite video sequences in real-time
• Work on perceptual layer of interactive agents
• Improve lip-sync accuracy, motion realism, and visual quality
• Build evaluation frameworks for quality tracking
• Collaborate with data team to define data needs
• Stay current with research in world models, interactive human/agent modeling

Perks and Benefits:

• Attractive compensation
• Hybrid work setting with offices in London, Zurich, and Munich
• 25 days of annual leave + public holidays
• Great company culture with regular social and planning events
• Generous referral scheme
• Strong opportunities for career growth