Deep Learning Compiler Intern - 2027
Salary not listed • China, Shanghai • Internship
Posted 1mo ago
Remote Work Policy
On-site
Employment Type
Internship
Categories
LLM Engineer
About the job
NVIDIA is seeking a Deep Learning Compiler Intern for 2027 to join our Architecture group. This role involves contributing to the development of cutting-edge GPU architectures and parallel programming models. You will be immersed in a supportive environment focused on innovation and making a lasting impact on the world through AI and accelerated computing.
Responsibilities
- Design and implement the DSL and core compiler for tile-aware GPU programming models for emerging GPU architectures.
- Continuously innovate and iterate on the compiler's core architecture to optimize performance.
- Investigate next-generation GPU architectures and propose solutions for the DSL and compiler stack.
- Explore optimal compiler/DSL forms for the era of agentic coding.
- Perform performance analysis on emerging AI/LLM workloads and integrate with AI/ML frameworks.
Requirements
- Master's or PhD or equivalent experience in a relevant discipline (CE, CS&E, CS, AI).
- Excellent C/C++ programming and software engineering skills.
- Good fundamental knowledge of computer architecture.
- Strong ability in abstracting problems and problem-solving methodologies.
- Strong compiler backgrounds including MLIR/TVM/Triton/LLVM is desired.
- Good knowledge of GPU architecture and fast kernel programming skills is a plus.
- Knowledge of LLM algorithms or a specific HPC domain is a plus.
- Knowledge of multi-GPU distributed communication is a plus.
- Familiarity with the agentic coding development workflow is a plus.
- Excellent oral communication in English is a plus.
Benefits
- Highly competitive salaries
- Comprehensive benefits package