About the Role
Job Details
Job Description:
Why Join Us
Join a team shaping the future of AI on Intel platforms. You will work on cutting-edge technologies that accelerate Large Language Models, Generative AI, and other advanced AI workloads on next-generation Intel GPUs. This role offers the opportunity to collaborate with experts across hardware architecture, compilers, runtime systems, and AI frameworks while developing skills that span the full AI software stack. Your work will have direct impact on delivering industry-leading AI performance and enabling the next generation of AI applications.
Intel is seeking a Senior AI Systems Software Engineer to drive optimization strategy and technical leadership across the AI software stack. In this role, you will lead the development of high-performance software solutions that accelerate AI inference workloads, including Large Language Models (LLMs), Generative AI, and emerging machine learning applications on Intel GPU platforms.
You will work across software, compilers, runtimes, frameworks, and hardware architecture teams to deliver breakthrough AI performance and influence future product direction.
What You'll Do
Key responsibilities will include but not limited to:
• Lead optimization initiatives for AI inference workloads on Intel GPUs.
• Define and drive performance optimization strategies across compilers, runtimes, and GPU kernels.
• Architect software solutions that improve scalability, efficiency, and performance.
• Profile, benchmark, and analyze complex AI workloads to identify system bottlenecks.
• Influence hardware and software co-design decisions through performance characterization and workload analysis.
• Drive cross-functional technical initiatives spanning architecture, compiler, framework, and runtime teams.
• Mentor engineers and provide technical leadership across projects.
• Evaluate emerging AI technologies and identify future optimization opportunities.
Behavioral Traits That We Are Looking For
• Demonstrates exceptional technical judgment and the ability to solve complex, high-impact challenges.
• Thinks strategically across the software and hardware stack, identifying opportunities to improve performance, scalability, and efficiency.
• Leads through influence, building alignment and driving outcomes across cross-functional organizations.
• Communicates effectively with both technical and business audiences, translating complex concepts into actionable insights.
• Operates with a strong sense of ownership and accountability, driving initiatives from strategy through execution.
• Uses data, experimentation, and measurable results to inform decisions and guide technical direction.
• Develops and elevates talent through mentorship, collaboration, and technical leadership.
• Brings an innovation mindset and a passion for advancing the future of AI computing.
Intel invests in our people and offers a complete and competitive package of benefits employees and their families through every stage of life.
• See Intel Benefits for more details.
Qualifications
You must possess the below minimum qualifications to be initially considered for this position. Preferred qualifications are in addition to the minimum requirements and are considered a plus factor in identifying top candidates.
Note
For information on Intel's immigration sponsorship guidelines, please see
Intel U.S. Immigration Sponsorship Information
Minimum Qualifications And Experience
Bachelor's degree in Computer Science, Computer Engineering, Electrical Engineering, or a related technical field with 5+ years or experience. Or a Master's degree in the same field with 3+ years of experience or a PhD in the same filed with 1+ years of experience.
Your Experience Described Above Must Be In The Following
• Experience in software development, AI systems, or performance engineering.
• C++ software development and debugging
• Experience with performance analysis, profiling, and optimization of compute-intensive applications.
• Experience with modern neural network architectures and their execution on hardware accelerators.
Preferred Qualifications And Experience
• GPU architectures, AI accelerators, or parallel computing systems.
• Experience optimizing end-to-end AI inference workloads in production environments.
• Familiarity with AI inference frameworks such as llama.cpp, vLLM, OpenVINO, PyTorch, TensorRT, ONNX Runtime, or similar technologies.
• Experience with graph compilation and optimization technologies such as MLIR, LLVM, TVM, XLA, or related compiler frameworks.
• Experience with GPU programming models such as Vulkan Compute, OpenCL, SYCL, CUDA, HIP or equivalent technologies.
• Knowledge of neural network optimization techniques, quantization, kernel fusion, memory optimization, and performance tradeoffs.
• Experience across multiple layers of the AI software stack, including:
• AI inference runtimes and serving frameworks
• Graph compilers and optimization frameworks
•