Senior Deep Learning Software Engineer, Inference

NVIDIA seeks a Senior Deep Learning Software Engineer to design and optimize GPU-accelerated inference software for large-scale AI models. The role involves contributing to open-source frameworks like vLLM and SGLang, optimizing performance across NVIDIA datacenter GPUs and edge SoCs, and collaborating with cross-functional teams on LLM and generative AI inference.

• Optimize, analyze, and tune deep learning models for LLM, multimodal, and generative AI inference.
• Scale performance of DL models across various NVIDIA accelerator architectures.
• Contribute features and code to NVIDIA inference libraries such as vLLM, SGLang, and FlashInfer.
• Collaborate with teams across frameworks, NVIDIA libraries, and inference optimization.

• Master's, PhD, or equivalent experience in computer engineering, computer science, EECS, or AI.
• 5+ years of relevant software development experience.
• Excellent C/C++ programming and software design skills.
• Experience with Python is a plus.

• Contributions to deep learning projects like PyTorch, vLLM, and SGLang.
• Experience with multi-GPU communication (NCCL, NVSHMEM).
• Experience building and shipping products to enterprise customers.