As a full-time Deep Learning Software Engineer specializing in Inference, the new college graduate will design, build, and optimize GPU-accelerated software for advanced AI applications, working remotely while contributing to high-performance open-source frameworks for model serving and inference. Key responsibilities: Optimize and analyze performance of deep learning models across various domains including LLM and Generative AI Scale performance of deep learning models on different NVIDIA accelerator architectures Contribute features and code to NVIDIA's inference libraries and collaborate with cross-functional teams on innovative solutions Required qualifications: Pursuing or recently completed a MS or PhD in Computer Engineering, Computer Science, EECS, AI, or a related field Software development experience with strong C/C++ programming and software design skills Experience with training, deploying, or optimizing inference of deep learning models in production is a plus Background in performance modeling, profiling, and code optimization, with knowledge of CPU and GPU architectures GPU programming experience (CUDA, OAI TRITON, or CUTLASS) is a plus