🛠 Tech Stack

💼 About This Role

You'll advance multimodal video generation at Mirage, working on novel modeling approaches for a platform used by millions of creators. Your core impact will be pushing generation quality, controllability, and realism in facial expression, audio-to-video sync, and human motion. You'll validate ideas through real-world product impact.

🎯 What You'll Do

• Develop novel approaches to video and multimodal generative modeling
• Design new training objectives, loss functions, and evaluation methods
• Explore temporal modeling, controllability, and multimodal alignment
• Conduct empirical studies to understand scaling behavior and model performance

📋 Requirements

• MS/PhD in ML, CS, or related field
• Strong publication record (NeurIPS, ICML, ICLR, etc.)
• Deep expertise in generative modeling (diffusion, autoregressive architectures)
• Deep understanding of transformers and modern multimodal systems

✨ Nice to Have

• Experience with large-scale training and empirical research
• Experience optimizing models for real-time inference efficiency
• Strong experience with audio representations and audio-visual datasets

🎁 Benefits & Perks

• 🏥 Comprehensive medical, dental, and vision plans
• 💰 401K with employer match
• 🍱 Catered lunch multiple days per week
• 🌴 Generous PTO policy
• 🏖️ Team offsites and monthly events

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Interview· 60 min
3. 3Onsite Interview· 3 hours