GenAI Algorithms Intern – Model Optimization for Inference

The GenAI Algorithms Intern role at NVIDIA focuses on optimizing generative AI models like LLMs and diffusion models for inference efficiency. The position involves designing and implementing optimization algorithms, integrating them into NVIDIA's software stack, and collaborating on solutions for customer use cases. The intern will work across multiple layers of the AI software stack, from algorithm design to integration, while contributing to open-source frameworks and potentially GPU-level optimization.