Senior DL Inference Engineer — GPU AI, Open Source, Equity

NVIDIA AI; California (MO); On-site; USD 150,000 - 240,000; Full time

Benefits offered by this job

Equity

Health Insurance

Comprehensive Benefits Package

Job summary

NVIDIA AI is seeking a senior GPU software engineer to design, build, and optimize GPU-accelerated software for AI applications. You will focus on high-performance open-source frameworks, improving deployment and serving platforms for language models and Generative AI workloads.

The role requires a PhD or Master’s in a relevant field and 5+ years of software development, with strong C/C++, GPU programming and DL experience, plus familiarity with CUDA and inference frameworks.

Qualifications

• Master's or PhD in a relevant field; 5+ years of software development experience.
• Strong skills in C/C++, experience with deep learning models, and familiarity with GPU programming.

Responsibilities

• Design, build, and optimize GPU-accelerated software for AI applications.
• Improve platforms for deploying and serving language models and Generative AI workloads.
• Drive performance improvements for LLM and Generative AI models.

Skills

Deep Learning

Software Engineering

C/C++

Python

Performance Optimization

GPU Programming

CUDA

Inference Frameworks

Model Serving

AI

Multimodal

Generative AI

Open Source

NVIDIA Accelerators

SW Agile

Performance Modeling

Education

Master's or PhD in a relevant field

Job description

NVIDIA AI is seeking a senior GPU software engineer to design, build, and optimize GPU-accelerated software for AI applications. You will focus on high-performance open-source frameworks, improving deployment and serving platforms for language models and Generative AI workloads.

The role requires a PhD or Master’s in a relevant field and 5+ years of software development, with strong C/C++, GPU programming and DL experience, plus familiarity with CUDA and inference frameworks.