Senior DL Inference Engineer - GPU/LLM Performance & Equity

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

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA seeks a Senior Software Engineer specializing in Deep Learning Inference to design, build, and optimize GPU-accelerated software powering AI applications. You will work on high-performance open-source frameworks, enabling efficient model serving and deployment across datacenters and edge devices.

You will collaborate with the deep learning community to implement the latest techniques for public release in inference frameworks and contribute to NVIDIA libraries such as vLLM, SGLang, and

Qualifications

• Masters or PhD (or equivalent) in Computer Engineering, Computer Science, EECS, AI.
• 5+ years of relevant software development experience.
• Excellent C/C++ programming and software design skills.
• Python experience is a plus; training/deploying inference experience is a plus.
• GPU programming with CUDA, OAI Triton or CUTLASS is a plus.

Responsibilities

• Performance optimization, analysis, and tuning of DL models across domains like LLM, Multimodal, and Generative AI.
• Scale DL model performance across architectures and NVIDIA accelerators.
• Contribute features and code to NVIDIA's inference libraries (e.g., vLLM, SGLang) and related tooling.
• Collaborate with cross-functional teams across frameworks, NVIDIA libraries, and inference optimization.

Skills

C/C++ programming

Software design

Python

CUDA programming

Performance modeling

DL inference

Education

Masters or PhD or equivalent (CS/EECS/AI)

Tools

CUTLASS

OAI Triton

NCCL

CUDA kernels

Job description

NVIDIA seeks a Senior Software Engineer specializing in Deep Learning Inference to design, build, and optimize GPU-accelerated software powering AI applications. You will work on high-performance open-source frameworks, enabling efficient model serving and deployment across datacenters and edge devices.

You will collaborate with the deep learning community to implement the latest techniques for public release in inference frameworks and contribute to NVIDIA libraries such as vLLM, SGLang, and