- Lead the design and implementation of deep learning models for motion capture, pose estimation, and generative motion synthesis.- Develop and optimize transformer-based architectures and multimodal AI systems for real-time inference and large-scale data processing.- Collaborate with research, animation, and engineering teams to translate experimental models into production-ready pipelines.- Develop scalable training and deployment systems using frameworks such as PyTorch, TensorRT, and gRPC.- Work with cross-functional partners to prototype, benchmark, and validate new models and algorithms for animation, capture, and simulation.- Implement best practices for data curation, synthetic dataset generation, and model evaluation.- Drive experimentation and innovation through close collaboration with academic institutions and industry partners.- PhD or Master’s degree in Computer Science, Engineering, or a related field, with focus on Machine Learning, Computer Vision, or Applied AI.- 5+ years of professional experience developing and deploying machine learning systems in production.- Proven expertise in deep learning for human motion capture, pose estimation, or 3D vision.- Proficiency in Python, PyTorch, TensorFlow, and deep learning optimization toolkits (e.g., TensorRT).- Strong understanding of transformer architectures, LLMs, and generative adversarial networks (GANs).- Demonstrated ability to lead R&D initiatives, mentor technical staff, and deliver results across multidisciplinary teams.- Excellent problem-solving, communication, and documentation skills.