Software Engineer Intern, AI and DL Kernel Libraries - 2027
Salary not listed • China, Shanghai • Internship
Posted 1mo ago
Job Location
China, Shanghai
Tech Stack
Remote Work Policy
On-site
Employment Type
Internship
Categories
Machine Learning Engineer
About the job
NVIDIA is seeking outstanding Software Engineer Interns to contribute to the development of groundbreaking technologies for AI and deep learning kernel libraries. The team focuses on building core software that accelerates high-impact AI workloads on NVIDIA GPUs, with an emphasis on deep learning primitives, kernel libraries, and performance-critical GPU software. Interns will engage in the design, development, optimization, and delivery of software integral to NVIDIA's AI platform, with opportunities to work on low-level kernels, performance primitives, and efficient implementations for modern AI and deep learning workloads. This role involves contributing to GPU-accelerated deep learning primitives, attention kernel implementations, runtime components, code generation systems, and performance-critical infrastructure for advanced AI applications, collaborating with world-class engineers across various AI software domains.
Responsibilities
- Contribute to production-quality software for NVIDIA's AI software stack, including cuDNN and FlashInfer.
- Develop new AI systems technologies for efficient inference, focusing on performance, scalability, and usability.
- Support the design, implementation, and optimization of kernels for high-impact AI workloads like LLM inference and generative AI.
- Assist in building extensible software abstractions for deep learning libraries and LLM serving engines.
- Contribute to just-in-time compilation, code generation, and runtime technologies for GPU workloads.
- Analyze workload performance, tune existing software, and propose improvements for future software and hardware-software interfaces.
- Collaborate with engineers across deep learning frameworks, libraries, kernels, compilers, and GPU architecture teams.
- Contribute to open-source communities and ecosystem integrations, including projects like FlashInfer and vLLM.
Requirements
- Currently pursuing a Bachelor's, Master's, or PhD degree in Computer Science, Electrical Engineering, or a related field.
- Coursework, research, or project experience in machine learning, deep learning systems, compilers, systems software, or GPU programming.
- Strong programming skills in C/C++ and Python.
- Familiarity with CUDA development and GPU programming fundamentals.
- Experience developing with or using deep learning frameworks such as PyTorch, JAX, TensorFlow, or ONNX.
- Understanding of linear algebra, performance analysis, profiling, and code optimization.
- Interest in software abstractions, APIs, and system architecture for performance-sensitive systems.
- Interest in modern machine learning and inference system trends, especially LLMs and generative AI.
- Strong problem-solving skills and ability to work effectively in a collaborative environment.