Rust Systems Engineer — GPU Compiler & Tooling

AMD; San Jose (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

AMD benefits

Job summary

AMD in San Jose, CA is seeking a deeply technical compiler and systems generalist to shape Rust usage across the GPU stack. You will work across rustc, MIR, MLIR, and LLVM-based backends to enable high-performance, safe GPU software.

Strong emphasis on correctness, memory safety, and hardware-software co-design will guide your decisions. The role spans debugging, testing, and validating across hardware interfaces, firmware, and software toolchains, with a path toward architectural influence and

Qualifications

• Strong production Rust experience and safe abstractions over unsafe operations.
• Experience with low-level or constrained Rust, including no_std and embedded contexts.
• Solid C/C++ systems programming skills and cross-language codebase experience.

Responsibilities

• Lead design and implementation of production-quality Rust components for low-level GPU systems.
• Advance Rust as a first-class language across GPU software stack, including toolchain integration and diagnostics.
• Design compiler pipelines using rustc, MIR, MLIR dialects, LLVM IR, and AMDGPU code generation.
• Develop analyses, transformations, and lowering passes for GPU execution models and memory spaces.
• Define interfaces across compiler, host runtime, device code, firmware, and hardware boundaries.

Skills

Rust

Rustc internals

GPU architectures

Compiler backends

MLIR/LLVM

Education

Bachelor's in CS

Tools

LLVM

MLIR

GCC

Rust toolchain

Job description

AMD in San Jose, CA is seeking a deeply technical compiler and systems generalist to shape Rust usage across the GPU stack. You will work across rustc, MIR, MLIR, and LLVM-based backends to enable high-performance, safe GPU software.

Strong emphasis on correctness, memory safety, and hardware-software co-design will guide your decisions. The role spans debugging, testing, and validating across hardware interfaces, firmware, and software toolchains, with a path toward architectural influence and