Staff Software Development Engineer - Rust, Compilers, and GPU Systems

Experteer Overview In this role you will help build next-generation systems software for AMD GPUs with Rust as a core direction. You’ll influence production Rust usage across the GPU stack, from compilers and runtimes to tooling and validation. You’ll work across abstraction layers, contributing to both near-term implementations and long-term architecture. This is a hands-on, cross-functional role that blends Rust systems programming with compiler infrastructure, GPU architecture, and firmware. You will join a mission-driven team delivering high-performance, safe, and scalable GPU software that enables AI, HPC, and cloud workloads. Compensation / Benefits * Lead design and implementation of production-quality Rust components for low-level, performance-sensitive GPU systems * Drive Rust as a first-class language across the GPU software stack (toolchain, libraries, diagnostics, testing, deployment) * Design and implement compiler pipelines (rustc, MIR, IRs, MLIR dialects, LLVM IR, AMDGPU codegen) * Develop analyses, transformations, legalization passes, and target-specific lowering for GPU execution models * Define typed, auditable interfaces across compiler, host runtime, device code, firmware, and hardware boundaries * Work on ABI definitions, argument layout, calling conventions, linker/loader behavior, ELF and code-object metadata * Develop or improve bare-metal/no_std Rust components for explicit, bounded, fail-closed behavior * Apply testing, fuzzing, differential execution, and hardware validation to prevent regressions * Use program analysis or formal methods to provide meaningful assurance and document trusted boundaries * Collaborate with compiler, runtime, firmware, architecture, validation, security, and performance teams to solve cross-boundary problems * Write design documents, lead technical reviews, mentor engineers, and clearly communicate complex concepts * Evaluate emerging compiler and verification technologies and integrate them when they improve safety, performance, or velocity Tasks * Strong production Rust experience (ownership/borrowing, lifetimes, traits/generics, concurrency, FFI, safe abstractions over unsafe) * Experience with no_std, embedded systems, firmware, or architecture-specific Rust targets * Strong C/C++ systems programming skills and cross-language collaboration * Experience with rustc internals, MIR, custom codegen backends, macros, or toolchain infrastructure * Experience with LLVM, MLIR, GCC or another production compiler framework * Experience designing IRs, dialects, analyses, optimizations, target-specific code generation * Understanding of compiler correctness issues (UB, aliasing, memory models, calling conventions) * Ability to read/reason about low-level assembly, ISA encodings, compiler output * Experience with linkers/loaders/ELF/code-object metadata, DWARF, post-link analysis or binary rewriting * Understanding GPU execution models (waves/warps, SIMD/SIMT, memory spaces, synchronization) * Experience with AMDGPU, GCN, RDNA, CDNA, ROCm, HIP, HSA, or AMDGPU LLVM backend * Experience with GPU runtimes, drivers, firmware, device init, command processing, queues * Experience with program analysis or formal verification tools (Verus, Lean, Coq, Isabelle, Dafny, TLA+) * Experience writing executable specifications and proving state-machine invariants * Strong validation instincts (adversarial testing, differential testing, fuzzing) * Hardware-software co-design experience for ISA features or compute pipelines * Technical leadership: setting direction, cross-layer problem solving, mentoring, tradeoff communication Key requirements *

Rust performance, or velocity Tasks * Strong production Rust experience (ownership/borrowing, lifetimes, traits/generics, concurrency, FFI, safe abstractions over unsafe) * Experience with no_std, embedded systems, firmware, or architecture-specific Rust targets * Strong C/C++ systems programming skills and cross-language collaboration * Experience with rustc internals, MIR, custom codegen backends, macros, or toolchain infrastructure * Experience with LLVM, MLIR, GCC or another production compiler framework * Experience designing IRs, dialects, analyses, optimizations, target-specific code generation * Understanding of compiler correctness issues (UB, aliasing, memory models, calling conventions) * Ability to read/reason about low-level assembly, ISA encodings, compiler output * Experience with linkers/loaders/ELF/code-object metadata, DWARF, post-link analysis or binary rewriting * Understanding GPU execution models (waves/warps, SIMD/SIMT, memory spaces, synchronization) * Experience a and AMDGPU, GCN, RDNA, CDNA, ROCm, HIP, HSA, or AMDGPU LLVM backend * Experience with GPU runtimes, drivers, firmware, device init, command processing, queues * Experience with program analysis or formal verification tools (Verus, Lean, Coq, Isabelle, Dafny, TLA+) * Experience writing executable specifications and proving state-machine invariants * Strong validation instincts (adversarial testing, differential testing, fuzzing) * Hardware-software co-design experience for ISA features or compute pipelines * Technical leadership: setting direction, cross-layer problem solving, mentoring, tradeoff communication Key requirements *