Senior AI Systems Engineer - GPU Inference Optimizations

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

Benefits offered by this job

Stock bonuses

Health benefits

Retirement plan

Vacation

Job summary

Intel Corporation is seeking a Senior AI Systems Software Engineer to accelerate AI inference on Intel GPUs and shape optimization across the software stack. You will lead performance improvements for LLMs, Generative AI, and related workloads, collaborating across hardware, compilers, runtimes, and AI frameworks.

This role offers a hybrid on‑site/off‑site work model in the United States. You’ll mentor engineers, influence product direction, and drive end‑to‑end optimization from kernels to

Qualifications

• Bachelor’s degree in CS/CE/EE or related field with 5+ years of exp, or higher degrees with fewer years.
• Experience in software development, AI systems, or performance engineering.
• C++ development and debugging; performance analysis and optimization.

Responsibilities

• Lead optimization initiatives for AI inference workloads on Intel GPUs.
• Define performance strategies across compilers, runtimes, and GPU kernels.
• Architect software solutions for scalability and efficiency.
• Profile and benchmark complex AI workloads to identify bottlenecks.
• Influence hardware-software co-design through workload analysis.
• Drive cross-functional technical initiatives across architecture, compiler, framework, and runtime teams.
• Mentor engineers and provide technical leadership across projects.

Skills

C++ development

Performance profiling

Neural nets

AI systems

Education

Bachelor's in CS/CE/EE

Master's in related field

PhD in related field

Tools

CUDA

HIP

OpenVINO

PyTorch

TensorRT

ONNX Runtime

Job description

Intel Corporation is seeking a Senior AI Systems Software Engineer to accelerate AI inference on Intel GPUs and shape optimization across the software stack. You will lead performance improvements for LLMs, Generative AI, and related workloads, collaborating across hardware, compilers, runtimes, and AI frameworks.

This role offers a hybrid on‑site/off‑site work model in the United States. You’ll mentor engineers, influence product direction, and drive end‑to‑end optimization from kernels to