Synthesia

Staff Research Engineer role at Synthesia, a leading AI video platform, focusing on post-training generative video creation. The role involves applying and adapting foundational models, implementing optimization techniques, and ensuring high-quality output for synthetic humans. Requires expertise in diffusion models, computer vision, and Python.

Research Engineer focused on avatar-centric interactive video diffusion models, aiming to turn breakthrough ideas into real product capabilities. Responsibilities include adapting diffusion models, developing real-time streaming methods, working on the perceptual layer for user interaction, improving visual quality, and building evaluation frameworks. Requires strong ML/CV background, PyTorch proficiency, and Python engineering skills.

Research Engineer role focused on post-training optimization of generative speech and voice synthesis models to achieve production-level quality, speed, and robustness. Involves adapting models for new inputs, fine-tuning with advanced techniques (DPO, LoRA), implementing post-training optimizations (quantization, pruning, distillation), integrating novel architectures, and designing evaluation metrics for TTS systems.