GenAI Algorithms Intern – Model Optimization For Inference Poland Warsaw

NVIDIA is seeking a GenAI Algorithms Intern to optimize state-of-the-art generative AI models for inference efficiency on its latest hardware platforms. The role involves designing and implementing model optimization algorithms, integrating them into NVIDIA's AI software stack, and collaborating with teams to achieve optimal accuracy-performance trade-offs. The intern will work across multiple layers of the AI software stack, from algorithm design to integration, and may also explore GPU-level optimization.