Deep Learning Software Engineer, Inference - New College Grad 2026

NVIDIA AI; California (MO); On-site; USD 140,000 - 190,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA AI is seeking a talented researcher to design, build, and optimize GPU-accelerated software for high-performance deep learning inference and large-scale model serving. You will focus on improvements for LLM and Generative AI models across NVIDIA accelerators and contribute to open-source inference libraries.

The ideal candidate holds a Master’s or PhD in a related field, demonstrates strong C/C++ skills, and brings GPU programming experience.

Qualifications

• Pursuing or recently completed a Master's or PhD in Computer Engineering, Computer Science, or a related field.
• Strong proficiency in C/C++ and software design is required, with experience in GPU programming or deep learning optimization a significant plus.

Responsibilities

• Design, build, and optimize GPU-accelerated software for high-performance deep learning inference and large-scale model serving, with focus on LLMs and Generative AI across NVIDIA accelerators.

Skills

Deep Learning Inference

C/C++

Python

GPU Programming

Performance Optimization

Model Serving

Software Design

Agile

Education

Master's or PhD in Computer Engineering, Computer Science, or related field

Tools

CUDA

OAI Triton

CUTLASS

NCCL

NVSHMEM

PyTorch

Job description

Design, build, and optimize GPU-accelerated software for high-performance deep learning inference and large-scale model serving. Focus on improving performance for LLM and Generative AI models across various NVIDIA accelerators and contributing to open-source inference libraries.

Requirements

Candidates should be pursuing or have recently completed a Master's or PhD in Computer Engineering, Computer Science, or a related field. Strong proficiency in C/C++ and software design is required, with experience in GPU programming or deep learning optimization being a significant plus.

Key Skills

• Deep Learning Inference
• C/C++
• Python
• CUDA
• OAI Triton
• CUTLASS
• NCCL
• Performance Optimization
• LLM
• Generative AI
• Software Design
• Agile
• GPU Programming
• Model Serving
• NVSHMEM
• PyTorch

Benefits

• Equity
• Benefits