Senior Compiler Engineer – GPU Compute

About the role

NVIDIA is dedicated to reinventing accelerated computing. Reinvention requires great technology and amazing people. As an NVIDIAN, you’ll be immersed in a diverse, supportive environment where everyone is inspired to do their best work. Come join the team and see how you can make a lasting impact on the world. We are searching for a Senior Compiler Engineer in our GPU Software organization. We deliver features and improvements that help NVIDIA hardware reach its full potential across a growing range of computational workloads, from deep learning and scientific computing to self-driving cars, video games, and virtual reality. Our compiler organization makes its mark on every GPU NVIDIA produces.

The CUDA programming language defines a unified programming model across a range of system configurations and hardware capabilities. The compiler translates parallel programs written in higher-level languages, like CUDA C++, into microcode optimized for fast execution on NVIDIA’s family of industry-leading GPU architectures. More and more of that code is now written with the help of AI agents, and the compiler front end is where developers and agents first meet the language. In this role, you will focus on the CUDA compiler front end, building language features, diagnostics, and capabilities that help both developers and agents write correct, high-performance GPU code. You’ll also have the opportunity to grow into other parts of the compiler stack, including the LLVM-based optimizer, code generation, and MLIR.

What you'll be doing:

- Build compiler capabilities that help AI agents generate high-performing, high-quality GPU code.

- Improve front-end diagnostics and compiler feedback so that developers and AI agents can understand and act on what the compiler tells them.

- Design and implement CUDA C++ language features and extensions in the compiler front end, including parsing, semantic analysis, and code generation to IR.

- Track and implement evolving C++ standards features, and make sure they work well with the CUDA programming model.

- Explore and contribute to all parts of the compiler stack, including optimization, back end, and MLIR, wherever the right solution lives.

- Partner and collaborate with other compiler, library, and developer tools teams in a dynamic environment to deliver high-quality, robust solutions.

What we need to see:

- Bachelor’s, Master’s, or Ph.D. in Computer Science, Computer Engineering, a related field, or equivalent experience.

- 5+ years of relevant work or research experience in compiler development.

- Hands-on experience with a production C or C++ compiler front end, such as Clang or GCC.

- Strong understanding of the C++ language, including templates, overload resolution, and modern C++ standards.

- Strong C/C++ programming and software design skills.

- Ability to work independently, define project goals and scope, and drive complex engineering efforts to production.