Research Scientist, Multi-Modal Human Understanding

Highlights

• Advance multi-modal AI to perceive, interpret and synthesize human behavior.
• Build video models for temporal reasoning and human behavior synthesis.
• Enable more natural human-computer interaction at global scale.

What they offer

• bonus
• equity
• benefits

Ideal candidate

A curious researcher passionate about human-centered AI who loves experimenting with vision and video to understand behavior and thrives taking ideas from formulation to evaluation.

Requirements

• Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
• 2+ years of experience in multi-modal AI research, including hands-on work with Vision-Language Models, video understanding, or human-centric AI systems
• 2+ years of experience implementing and training large-scale neural networks using frameworks such as PyTorch, with experience on transformer-based architectures
• Experience designing and executing experiments to evaluate multi-modal model performance, including quantitative analysis across vision, language, and video benchmarks
• Experience writing production-quality or research-quality code in Python for multi-modal AI applications