Deep Learning Engineer - LLM and VLM Model Compression

This role is for a Deep Learning Engineer at NVIDIA, building frameworks for large language and vision language model compression. Daily tasks include designing and implementing frameworks, developing algorithms, and collaborating with researchers. Required skills include 8+ years of deep learning experience, Python programming, and knowledge of DL frameworks. Nice-to-haves include model compression techniques and GPU programming. This role is unique due to its focus on AI efficiency and access to powerful GPU clusters. NVIDIA offers a desirable work environment and equal opportunities.