Senior Deep Learning Software Engineer, Inference

Stack

Responsibilities

• ▹develop deep learning inference frameworks
• ▹extend SGLang and vLLM platforms
• ▹optimize performance of LLM and generative AI models
• ▹build model serving pipelines
• ▹integrate open-source tools (CUTLASS, Triton, NCCL, CUDA)
• ▹collaborate with the deep learning community

Requirements

• ▹MS/PhD or equivalent experience in a related field
• ▹5+ years of software development experience
• ▹excellent C/C++ programming and design skills
• ▹Python experience a plus

Nice to have

• ▹experience training, deploying or optimizing DL models in production
• ▹performance profiling and CPU/GPU architecture knowledge
• ▹contributions to PyTorch, vLLM, SGLang
• ▹multi-GPU communication (NCCL, NVSHMEM)
• ▹GPU programming (CUDA, OAI Triton, CUTLASS)

Soft skills

What we offer

• ▹highly competitive salary
• ▹extensive benefits package
• ▹flexible, inclusive work environment

About the company

NVIDIA is at the forefront of breakthroughs in Artificial Intelligence, High-Performance Computing, and Visualization.