Senior Deep Learning Software Engineer, Inference

Senior Software Engineer specializing in Deep Learning Inference at NVIDIA. Responsibilities include designing, building, and optimizing GPU-accelerated software for AI applications. Work on high-performance deep learning frameworks including SGLang and vLLM for efficient large-scale model serving and inference. Implement latest algorithms for public release, identify and drive performance improvements for state-of-the-art LLM and Generative AI models across NVIDIA accelerators. Focus areas: performance optimization and tuning of DL models (LLM, Multimodal, Generative AI), scaling performance across different NVIDIA accelerator architectures, contributing to NVIDIA's inference libraries (vLLM, SGLang, FlashInfer), and collaborating with cross-functional teams on inference optimization solutions.