Senior Research Engineer - Interactive Avatar Diffusion

You're joining a fast-paced AI R&D team focusing on avatar-centric interactive video diffusion models. You will adapt diffusion models with diverse conditioning signals (audio, motion, interaction cues), develop methods for streaming long video sequences in real time, and enhance perceptual aspects such as lip-sync, motion realism, and overall visual quality. You will build robust evaluation frameworks, collaborate with data teams to define data needs, and push research breakthroughs toward product impact. Requirements include strong ML background in diffusion, GANs, or VAEs; proficiency in PyTorch and Python; excellent communication of hypotheses, experiments, and results; and a track record of owning end-to-end model development from data preparation to evaluation and deployment.