Senior Deep Learning Engineer — Inference & Model Optimization

NVIDIA Corporation; Santa Clara (CA); On-site; USD 184,000 - 357,000; Full time

Job summary

NVIDIA is seeking a Senior Deep Learning Software Engineer to develop and scale automated inference and deployment solutions. You will train, develop, and deploy state-of-the-art generative AI models like LLMs and diffusion models using NVIDIA's AI software stack, and optimize inference with high-performance kernels in CUDA, TRT-LLM, and Triton.

You will collaborate across NVIDIA to push performance and user experience.

Qualifications

• Masters, PhD, or equivalent in CS/AI.
• 8+ years of deep learning experience.
• Strong Python, PyTorch, and ML tooling experience.

Responsibilities

• Train, develop, and deploy state-of-the-art generative AI models with NVIDIA's stack.
• Develop high-performance inference and deployment techniques for large models.
• Leverage the Torch 2.0 ecosystem (TorchDynamo, torch.export, torch.compile) for automated deployment.
• Analyze and optimize GPU kernel performance across NVIDIA platforms.
• Collaborate with cross-functional teams to extend model support and optimization techniques.

Skills

Python

PyTorch

HuggingFace

Education

Masters/PhD or equivalent

Tools

CUDA

Triton

TorchDynamo

TensorRT

Job description

NVIDIA is seeking a Senior Deep Learning Software Engineer to develop and scale automated inference and deployment solutions. You will train, develop, and deploy state-of-the-art generative AI models like LLMs and diffusion models using NVIDIA's AI software stack, and optimize inference with high-performance kernels in CUDA, TRT-LLM, and Triton.

You will collaborate across NVIDIA to push performance and user experience.