Senior Rust-to-GPU Compiler Engineer — Equity

NVIDIA; California (MO); On-site; USD 152,000 - 242,000; Full time

Benefits offered by this job

Equity

Benefits package

Job summary

NVIDIA is seeking a Senior Compiler Engineer to advance the next generation of GPU systems programming. You will design and implement Rust-to-GPU compiler pipelines, backends, and Rust-native IRs to compile Rust directly to CUDA PTX and machine code, enabling memory-safe, high-performance kernels.

You will drive IR design, optimizations, and end-to-end toolchains, while collaborating across teams to extend Rust ownership models across GPU launch boundaries and provide safe device-side

Qualifications

• 5+ years of compiler development or GPU code generation.
• Deep expertise in Rust, rustc, MIR and borrow-checker lifetime model.
• Experience with LLVM IR, MLIR, or custom IR systems.
• Strong knowledge of parallel GPU architectures and CUDA.
• Excellent debugging, profiling, and benchmarking skills.

Responsibilities

• Develop Rust-to-GPU compiler pipelines and backends.
• Build IRs and optimizers for GPU code.
• Support AOT, JIT, and LTO workflows across NVIDIA GPUs and host platforms.
• Define safe parallel abstractions across the GPU launch boundary.
• Expose device-side Rust abstractions for shared memory and warp-level operations.
• Collaborate to build future compiler-engineering building blocks.

Skills

Rust programming

Compiler development

CUDA programming

IRs/IR frameworks

Debugging & profiling

Independent work

Education

Bachelor's degree in CS/CE or equivalent

Master's degree

PhD in related field

Tools

MLIR

LLVM IR

Rustc

Procedural macros

Job description

NVIDIA is seeking a Senior Compiler Engineer to advance the next generation of GPU systems programming. You will design and implement Rust-to-GPU compiler pipelines, backends, and Rust-native IRs to compile Rust directly to CUDA PTX and machine code, enabling memory-safe, high-performance kernels.

You will drive IR design, optimizations, and end-to-end toolchains, while collaborating across teams to extend Rust ownership models across GPU launch boundaries and provide safe device-side