Senior Deep Learning Inference Engineer — GPU AI Systems + Equity

NVIDIA Corporation; Washington (District of Columbia); Hybrid; USD 184,000 - 288,000; Full time

Benefits offered by this job

Equity

Comprehensive benefits

Hybrid work policy

Job summary

NVIDIA seeks a Senior Software Engineer specializing in Deep Learning Inference for our growing team. You will design, build, and optimize GPU-accelerated software powering today’s AI applications, including inference frameworks and high-performance open-source tools.

Work across NVIDIA libraries and cross-functional teams to implement algorithms for public release, optimize model serving for LLMs and Generative AI, and improve performance on datacenter GPUs to edge devices.

Qualifications

• Masters or PhD in Computer Science, Computer Engineering, EECS or AI.

Responsibilities

• Performance optimization, analysis, and tuning of DL models.
• Scale performance across architectures and NVIDIA accelerators.
• Contribute features to NVIDIA's inference libraries and solutions.
• Collaborate with frameworks, libraries, and optimization teams.

Skills

C/C++ programming

Software design

Python experience

Agile practices

GPU programming (CUDA/WebGPU)

CUDA kernels

Education

Masters or PhD in CS/Engineering/AI

Tools

CUTLASS

OAI Triton

NCCL

SGLang

vLLM

Job description

NVIDIA seeks a Senior Software Engineer specializing in Deep Learning Inference for our growing team. You will design, build, and optimize GPU-accelerated software powering today’s AI applications, including inference frameworks and high-performance open-source tools.

Work across NVIDIA libraries and cross-functional teams to implement algorithms for public release, optimize model serving for LLMs and Generative AI, and improve performance on datacenter GPUs to edge devices.