Continuously keeping up to date on the latest advancements in generative AI research.
Analyzing and prototyping emerging workloads in multi-agent AI systems, generative multimodal models, and inference-time compute scaling.
Pioneering and developing optimizations for these workloads across the inference stack to push the boundaries of inferencing quality and speed on NVIDIA systems.
Collaborating closely with production teams to incorporate the latest advancements into cutting-edge software frameworks.
Requirements
Master's degree (or equivalent experience) in Computer Science, Artificial Intelligence, Applied Mathematics, or related fields.
A strong foundation in deep learning, with a particular emphasis on generative models and inferencing.
A track record of at least 5 years of relevant software development experience in modern deep learning frameworks such as PyTorch.