Principal Software Engineer, AI Compute Graph Compiler

Quick Facts

• Role: Principal Software Engineer (AI Compute Graph Compiler)

• Focus: Windows ML compiler stack and AI execution infrastructure across CPU/GPU/NPU

• Scope: Architecture, technical strategy, performance/efficiency optimization, and cross-team leadership

Description

You will define and drive the technical vision, architecture, and roadmap for key components of the Windows ML compiler stack, including compiler infrastructure, execution runtimes, optimization frameworks, and hardware abstraction. You will lead cross-team initiatives to improve ML workload performance, scalability, and efficiency across CPU, GPU, and NPU, with a strong emphasis on NPU enablement and advanced optimization. You will design and develop high-performance compiler infrastructure and execution engines while mentoring engineers and influencing long-term on-device and generative AI execution strategy.

Responsibilities

• Define and drive the technical vision, architecture, and roadmap for the Windows ML compiler stack

• Lead cross-team initiatives to improve AI workload performance, scalability, and efficiency across CPU/GPU/NPU

• Drive NPU enablement strategy and advanced optimization techniques for next-generation AI processors

• Partner with hardware vendors and internal platform teams to influence future AI hardware and software capabilities

• Design and develop high-performance compiler infrastructure, execution engines, and developer tooling

• Solve complex systems challenges across scheduling, memory management, code generation, graph optimization, and hardware abstraction

• Mentor engineers and provide technical leadership across multiple projects and organizations

• Help shape long-term strategy for on-device AI and generative AI execution on Windows

Requirements

• Bachelor’s degree in Computer Science or related technical field

• 6+ years technical engineering experience with production-quality systems software, AI/ML platforms, or related technologies (or equivalent experience)

• Demonstrated experience delivering production-quality systems software / AI-ML platforms

• Committed hands-on experience with ML compilers, runtimes, frameworks, tools, and platform technologies

• In-depth OS development experience, including user-mode and/or kernel-mode driver development

• Experience designing ML accelerator or hardware microarchitecture for real-world products and connecting hardware with compilers, runtimes, drivers, and frameworks

• Knowledge of computer architecture, heterogeneous computing, memory systems, parallel processing, and hardware/software co-design

• Proven experience optimizing ML workloads across the full stack, including GPU optimization

• Track record of technical leadership from prototype through production for AI platforms or accelerators

Benefits

• Compensation and benefits may be available; see provided pay/benefits information for the role

• Base pay range (U.S.): USD $142,800 – $274,800 per year

• Base pay range (San Francisco Bay Area / NYC metro): USD $188,000 – $304,200 per year