Lead the design and development of large video modelbased solutions for video and audio understanding to support content production, generation, and personalization
Innovate and build proof-of-concepts leveraging generative AI applications, driving them through full productionization
Develop and implement AI-powered video enhancement and manipulation algorithms such as super-resolution, automatic editing, colorization, and AI-driven content generation
Architect scalable and efficient systems for long-form video processing using advanced vision-language models and streaming encoding techniques
Establish best practices for model deployment, evaluation, monitoring, and continuous improvement in production environments
Optimize GPU-based AI/ML workloads and distributed processing pipelines for high-performance computing
Collaborate with cross-functional teams to align AI strategy with business and product goals
Represent the organization in industry forums and technical discussions related to video AI and large language models
