GPU Compiler Development Engineer

AMD
Beijing
Workplace: OnsiteFull timeCNY 411,670 - 588,100 annuallyFunction: Product ManagementEducation: bachelorsSkills: ["Effective communication","Problem-solving","Attention to detail"]

Build and optimize GPU compiler work within the ROCm Execution Provider, which runs large language and vision models on AMD GPUs via ONNX Runtime. Implement and unit-test ONNX operator lowerings in MLIR, then close per-operator performance gaps against competitive runtimes. Collaborate with GPU compiler, MLIR, and kernel teams to debug issues, develop new technologies, and stay current on software/hardware trends, including algorithms and architecture.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
AMD
AMD
2 months ago

GPU Compiler Development Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 18 hours agoStatus: Live

Job Summary

Build and optimize GPU compiler work within the ROCm Execution Provider, which runs large language and vision models on AMD GPUs via ONNX Runtime. Implement and unit-test ONNX operator lowerings in MLIR, then close per-operator performance gaps against competitive runtimes. Collaborate with GPU compiler, MLIR, and kernel teams to debug issues, develop new technologies, and stay current on software/hardware trends, including algorithms and architecture.
Location: Beijing
Workplace: Onsite
Employment Type: Full time
Job Function: Product Management

Key Responsibilities

  • •Work with AMD architecture specialists to improve future products.
  • •Implement and unit-test ONNX operator lowerings in MLIR.
  • •Apply a data-minded approach to close per-operator performance gaps versus competitive runtimes.
  • •Stay informed of software and hardware trends and innovations, especially around algorithms and architecture.
  • •Design and develop new AMD technologies; participate in new ASIC and hardware bring ups.

Pay and Benefits

Salary: CNY 411,670 - 588,100 annually

Key Requirements

  • •Strong object-oriented programming background with C/C++ preferred.
  • •Working knowledge of MLIR or LLVM and GPU or parallel programming.
  • •Experience implementing and unit-testing ONNX operator lowerings in MLIR.
  • •Familiarity with HIP/CUDA, ONNX/ONNX Runtime, and performance profiling/optimization is a plus.
  • •Bachelor’s or Master’s degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent.
Experience:GPUMLAIONNX
Education:Bachelor's in Computer Science, Computer Engineering, Electrical Engineering, or equivalent
Skills:Effective communicationProblem-solvingAttention to detail
Languages:English
Tech Stack:CC++MLIRLLVMGPUONNXONNX RuntimeROCm Execution ProviderHIPCUDAPerformance profilingWindowsLinuxGitHubASIC

Company Brief

AMD
Designs and produces semiconductor products including CPUs, GPUs, and adaptive SoCs for consumer, enterprise, and embedded markets, competing across PCs, data centers, and gaming industries.
Industry: Electronics Manufacturing
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Public Company
Valuation: Public Company (Market Cap in USD)
Funding: IPO / Publicly Listed
Headquarters: Santa Clara, United States
Founded: 1969
Glassdoor
Glassdoor: 3.9
WebsiteLinkedIn