JOBSEARCHER

Senior Deep Learning Software Engineer, Inference

NVIDIAMiami, FLL6 LeadSeptember 15th, 2026
Overview: In this role you will design, implement and optimize GPU-accelerated software powering state-of-the-art AI applications. You contribute to high-performance DL inference frameworks (SGLang, vLLM) and related tools, shaping reliable model serving at scale. You work across NVIDIA accelerators and open-source components to drive efficient deployment of cutting-edge language models. You will collaborate with cross-functional teams to apply the latest algorithms and achieve performance breakthroughs in inference. This is a mission-driven opportunity to impact large-scale AI systems and enterprise deployments. Compensation / Benefitsequitybenefitsremote work option
Responsibilities:
  • Performance optimization, analysis, and tuning of DL models across domains (LLM, Multimodal, Generative AI)
  • Scale DL model performance across architectures and NVIDIA acceleratorsContribute features and code to NVIDIA inference libraries (vLLM, SGLang, FlashInfer, LLM solutions)
  • Collaborate with cross-functional teams across frameworks and NVIDIA libraries to innovate inference solutions
Key requirements: 5+ years of relevant software development experienceExcellent C/C++ programming and software design skillsPython experience is a plusExperience with training, deploying or optimizing DL model inference in production is a plusPerformance modeling, profiling, debugging, and CPU/GPU architectural knowledge is a plusMasters or PhD (or equivalent experience) in Computer Engineering, Computer Science, EECS or AICollaborative and cross-functional teamworkStrong debugging and profiling mindsetResult-oriented with a focus on performance impactCUDACUTLASSNCCL