← Back to list
Job
· Principal
Staff Research Engineer - Video Post Training
AI / ML Engineer
• Principal
• Remote
• Full-time
• 📍 Europe
Synthesia, the world's leading AI video platform for business, is hiring a Staff Research Engineer to join a 40+ person R&D team working on cutting-edge Generative AI, focused on creating highly realistic, emotional, and life-like synthetic humans through text-to-video. The role sits on the applied side of research within the Post-Training Team for generative video creation, making it possible to apply foundational models to production use cases. It suits an expert in post-training Diffusion models for generative AI.
Responsibilities
- ▹Apply DPO (direct preference optimisation) to pre-trained models
- ▹Adapt models to extend their capabilities, for instance by changing conditioning inputs
- ▹Build solutions for dubbing and evaluate the quality of lip-sync
- ▹Implement post-training optimization techniques such as quantization, pruning, and distillation to improve the efficiency of diffusion models used in avatar generation
- ▹Analyze and address challenges related to model performance, ensuring high-quality output in avatar rendering
- ▹Stay updated with the latest research and advancements in diffusion models, adversarial networks, and post-training optimization methods
Requirements
- ▹Background in Computer Vision / Computer Science and 3+ years of industry experience
- ▹Knowledge of recent advancements in post-training techniques (for instance distillation, adversarial networks, and efficient attention)
- ▹Experience with generative models for images and/or videos (Diffusion/GAN), preferably in the avatar domain
- ▹Interest in doing research, trying new things, and pushing the boundaries beyond what is already known
- ▹Experience using most modern frameworks for machine learning and deep learning
- ▹Great coding skills in Python and care for writing clean code
- ▹Experience with SDLC tools (Git), preferably CI/CD
Soft skills
Research curiosity and willingness to push boundariesCare for clean, high-quality codeCollaboration within a large R&D team
What we offer
- ▹Competitive compensation (salary + stock options)
- ▹Hybrid work setting with an office in London, Amsterdam, Zurich, or Munich, or remote in Europe
- ▹25 days of annual leave plus public holidays
- ▹Strong company culture with regular planning and socials at the hubs, plus other location-dependent benefits
Education: Background in Computer Vision / Computer Science