AI GPU Software Engineer - Kernel & Compiler Optimizations

Intel Corporation; Folsom (CA); Hybrid; USD 150,000 - 276,000; Full time

Benefits offered by this job

Competitive pay

Stock bonuses

Health insurance

Retirement plan

Vacation

Job summary

Intel Corporation is seeking an AI Software Development Engineer to optimize AI inference workloads for Intel GPUs and improve performance across the full AI software stack in California, Folsom.

You will design and tune performance-critical GPU kernels, work with C++, SYCL, Vulkan Compute, OpenCL, and contribute to open-source frameworks like OpenVINO and PyTorch. This role features a hybrid work model in the US.

Qualifications

• Bachelor's degree in Computer Science, Computer Engineering, Electrical Engineering, or related field.
• 4+ years of relevant industry experience; or advanced degree with reduced experience.
• Experience with performance analysis and optimization for compute-intensive apps.

Responsibilities

• Optimize AI inference workloads for Intel GPUs.
• Design and tune GPU kernels and runtimes using C++, SYCL, Vulkan Compute, or OpenCL.
• Develop and optimize graph compilation flows and compiler passes (MLIR/LLVM).
• Identify and resolve performance bottlenecks across compiler, runtime, framework, and kernel layers.
• Profile, benchmark, and analyze AI workloads to guide optimization strategies.
• Collaborate with hardware, driver, compiler, and framework teams for co-optimization.
• Contribute to open-source AI inference frameworks such as OpenVINO, PyTorch, or ONNX Runtime.

Skills

C++ programming

GPU architectures

Performance profiling

Parallel computing

AI inference optimization

Cross-team collaboration

Education

Bachelor's degree in CS/Engineering

Master's or PhD preferred

Tools

OpenVINO

PyTorch

TensorRT

ONNX Runtime

MLIR/LLVM

Job description

Intel Corporation is seeking an AI Software Development Engineer to optimize AI inference workloads for Intel GPUs and improve performance across the full AI software stack in California, Folsom.

You will design and tune performance-critical GPU kernels, work with C++, SYCL, Vulkan Compute, OpenCL, and contribute to open-source frameworks like OpenVINO and PyTorch. This role features a hybrid work model in the US.