Senior Rust-to-GPU Compiler Architect (IR/MLIR)

NVIDIA; Washington; On-site; USD 152,000 - 242,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is hiring a Senior Compiler Engineer to drive the next generation of GPU systems programming. You will design Rust-to-GPU compiler pipelines and backends, enabling Rust-native IR frameworks to target CUDA PTX and machine code.

You will work on MLIR/LLVM IR, GPU-specific optimizations, and safe parallel abstractions across the GPU launch boundary, shaping memory safety and performance for high-end NVIDIA GPUs. Competitive salary and equity are offered.

Qualifications

• BS, MS, or PhD in Computer Science, Computer Engineering, or related field, or equivalent experience.
• 5+ years of compiler development, language design, or GPU code generation.
• Deep expertise in Rust, including rustc, MIR, and borrow-checker concepts.
• Hands-on experience with compiler infrastructures and IRs (LLVM IR/MLIR) and code generation.
• Solid understanding of parallel programming models and CUDA.
• Strong software design, debugging, profiling, and benchmarking skills.

Responsibilities

• Design, implement, and maintain Rust-to-GPU compiler backends and IR frameworks.
• Lower Rust AST and MIR into IRs such as MLIR, PTX, and LLVM with GPU optimizations.
• Support AOT, JIT, and link-time optimization workflows for NVIDIA GPUs.
• Define safe parallel abstractions across the GPU launch boundary to ensure memory safety.
• Expose device-side abstractions for low-level GPU primitives and shared memory.
• Collaborate across teams to translate requirements into production-ready compiler features.

Skills

Rust

Compiler internals

GPU code generation

LLVM/MLIR

Procedural macros

Education

Bachelor's/Master's/Ph.D. in CS/CE or related field

Tools

rustc

LLVM IR

MLIR

Procedural macros

Job description

NVIDIA is hiring a Senior Compiler Engineer to drive the next generation of GPU systems programming. You will design Rust-to-GPU compiler pipelines and backends, enabling Rust-native IR frameworks to target CUDA PTX and machine code.

You will work on MLIR/LLVM IR, GPU-specific optimizations, and safe parallel abstractions across the GPU launch boundary, shaping memory safety and performance for high-end NVIDIA GPUs. Competitive salary and equity are offered.