Software Engineer, DL Kernel Libraries - New College Grad 2027

NVIDIA is building software infrastructure to accelerate deep learning inference and training at scale, and the DL Kernel Libraries team plays a central role in that effort. As a Software Engineer Intern for the 2027 New College Grad program, you will help develop the systems software stack behind efficient AI workloads, including GPU kernel technologies, libraries, and supporting code generation.

This onsite role is based in Santa Clara, CA, with an estimated salary range of USD 108,000 - 195,500 per year.

What you’ll do

• Innovate and develop new AI systems technologies focused on efficient inference and training
• Design, implement, and optimize kernels for high impact AI workloads
• Design and implement extensible abstractions for serving engines and training frameworks
• Build efficient just-in-time domain specific compilers and runtimes
• Collaborate closely with other NVIDIA engineers across deep learning frameworks, libraries, kernels, and GPU architecture teams
• Contribute to open source communities including FlashInfer, cuDNN, vLLM, SGLang, PyTorch, JAX, and XLA

Requirements

• BS, MS, or PhD degree in Computer Science, Electrical Engineering, or related field (or equivalent experience)
• Strong experience developing or using deep learning frameworks (for example PyTorch, JAX, TensorFlow, ONNX) or inference engines and runtimes such as vLLM, SGLang, and MLC
• Strong Python and C/C++ programming skills

Technologies you may work with

• PyTorch, JAX, TensorFlow, ONNX
• vLLM, SGLang, MLC
• Python, C/C++, CUDA C/C++
• FlashInfer, cuDNN
• CUDA, CUTLASS DSL, cuTile, Triton
• Flash Attention, Apache TVM, MLIR
• XLA

Benefits

• Eligible for equity and benefits

Ways to stand out

• Background in domain specific compiler and library solutions for LLM inference and training (for example FlashInfer, Flash Attention)
• Expertise in training frameworks and inference engines
• Expertise in machine learning compilers (for example Apache TVM, MLIR)
• Strong experience in GPU kernel development and performance optimization, including experience with CUDA C/C++, CUTLASS DSL, cuTile, Triton, or similar
• Open source project ownership or contributions