You will be expected to advance human interaction modeling across various fronts, at a system level, and at a core ML algorithm level. Some of the myriad challenges include perceiving subtle cues in gaze, affect, or prosody, handling deeply interleaved streaming inputs, reasoning over varying temporal contexts, developing memory systems to enable long-term adaptation, generating semantically rich internal representation to enable open-ended downstream tasks, etc.You will be responsible for delivering solutions that can readily be adopted in production pipelines, such as APIs for production-ready ML models, or algorithms well integrated into training infrastructure.