NVIDIA Spring 2027 Internships: Developer and Performance Technology
Core
Interns run performance, image quality, and power tests for Professional Visualization, AI, and LLM benchmark applications on various GPUs; configure systems, build automation scripts, and develop tools for benchmarking procedures.
Role type
Intern, Performance Engineering and Deep Learning
Builds
Benchmarking procedures, automation scripts, test systems, and performance reports for GPU platforms
Domain
Hardware engineering, Deep Learning, High-Performance Computing (HPC)
Deliverable
production ML models
Required skills
GPU Programming (CUDA, OpenCL), Python/Unix Shell Scripting, Linux, Containers (Docker, Singularity), Debugging, Benchmarking, Power Testing, Electrical Fundamentals, 3D Graphics, Low Level System Configuration
Preferred skills
GPU Accelerated Deep Learning Frameworks (TensorFlow, PyTorch, MXNet, TensorRT), HPC Applications (LAMMPS, GROMACS, Amber), Compilers (GNU, Intel Composer, PGI), Clusters (Slurm, Kubernetes), Embedded Platforms
Technologies
NVIDIA GPUs, Linux, Python, CUDA, OpenCL, Docker, Singularity, TensorFlow, PyTorch, MXNet, TensorRT, LAMMPS, GROMACS, Amber, Slurm, Kubernetes, GNU, Intel Composer, PGI
Responsibilities
Running performance, image quality, and power tests for benchmark applications; Configuring computer systems with appropriate hardware and software; Building automation scripts for benchmarking procedures; Assembling computer hardware and developing automation scripts; Completing post-silicon performance and power benchmarking; Compiling and analyzing data for internal groups; Developing and maintaining test systems; Writing scripts to improve data gathering through automation
Seniority
Intern
